LangBot EBA Adapter Development
langbot-app/LangBot
Guides building, migrating and testing LangBot messaging-platform adapters for the Event-Based Agents layout, with unified event and message conversion.
Choose or maintain repository Make/script workflows, builds, dependency selection, generated artifacts, and security CLI tools.
$ npx skills add greenpau/caddy-security --skill scripts-and-automation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install greenpau/caddy-security scripts-and-automation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/greenpau/caddy-security.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/scripts-and-automation .claude/skills/scripts-and-automation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "scripts-and-automation" agent skill from https://github.com/greenpau/caddy-security/tree/main/.codex/skills/scripts-and-automation into .claude/skills/scripts-and-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scripts-and-automation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/greenpau/caddy-security/tree/main/.codex/skills/scripts-and-automationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add greenpau/caddy-security --skill scripts-and-automation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install greenpau/caddy-security scripts-and-automation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/greenpau/caddy-security.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.codex/skills/scripts-and-automation .agents/skills/scripts-and-automation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scripts-and-automation" agent skill from https://github.com/greenpau/caddy-security/tree/main/.codex/skills/scripts-and-automation into .agents/skills/scripts-and-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scripts-and-automation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add greenpau/caddy-security --skill scripts-and-automation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install greenpau/caddy-security scripts-and-automation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/greenpau/caddy-security.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.codex/skills/scripts-and-automation .cursor/skills/scripts-and-automation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "scripts-and-automation" agent skill from https://github.com/greenpau/caddy-security/tree/main/.codex/skills/scripts-and-automation into .cursor/skills/scripts-and-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scripts-and-automation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/greenpau/caddy-security.git --path .codex/skills/scripts-and-automation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add greenpau/caddy-security --skill scripts-and-automation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install greenpau/caddy-security scripts-and-automation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/greenpau/caddy-security.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.codex/skills/scripts-and-automation .gemini/skills/scripts-and-automation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "scripts-and-automation" agent skill from https://github.com/greenpau/caddy-security/tree/main/.codex/skills/scripts-and-automation into .gemini/skills/scripts-and-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scripts-and-automation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install greenpau/caddy-security scripts-and-automationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add greenpau/caddy-security --skill scripts-and-automation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/greenpau/caddy-security.git skills-src && mkdir -p .github/skills && cp -r skills-src/.codex/skills/scripts-and-automation .github/skills/scripts-and-automation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "scripts-and-automation" agent skill from https://github.com/greenpau/caddy-security/tree/main/.codex/skills/scripts-and-automation into .github/skills/scripts-and-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scripts-and-automation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add greenpau/caddy-security --skill scripts-and-automation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install greenpau/caddy-security scripts-and-automation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/greenpau/caddy-security.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.codex/skills/scripts-and-automation .opencode/skills/scripts-and-automation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "scripts-and-automation" agent skill from https://github.com/greenpau/caddy-security/tree/main/.codex/skills/scripts-and-automation into .opencode/skills/scripts-and-automation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scripts-and-automation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
scripts-and-automationChoose or maintain repository Make/script workflows, builds, dependency selection, generated artifacts, and security CLI tools.
Scripts And Automation is an agent skill from greenpau/caddy-security. Choose or maintain repository Make/script workflows, builds, dependency selection, generated artifacts, and security CLI tools. Routes release work and documents local administration and standalone login commands.
Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `agents/openai.yaml`, `references/caddy-authenticator.md` and `references/codeql.md`).
It sits in Backend & APIs. The repository describes itself as: 🔐 Authentication, Authorization, and Accounting (AAA) App and Plugin for Caddy v2. 💎 Implements Form-Based, Basic, Local, LDAP, OpenID Connect, OAuth 2.0 (Github, Google…. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit a48553d. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
makegoFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Scripts And Automation loads about 4.9k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 2,337 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from greenpau/caddy-security at commit a48553d, republished under its Apache-2.0 licence (© greenpau). 2,337 words, ~4,860 tokens.
.claude/skills/scripts-and-automation/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.Use headless Chrome for browser automation and screenshot/network evidence.
Avoid Firefox unless explicitly requested for a browser-specific task. Follow
the testing browser guidance for
private profiles, reproducible tool pins and strict TLS trust. Keep all downloaded
browser tools and generated data in this repository's tmp/; do not install
browser packages or trust roots system-wide for a test run.
Use the Makefile as the primary automation surface for this Go module. This
repository builds a Caddy command binary at bin/authcrunch from
cmd/authcrunch/main.go; the binary registers the security app, the
authenticate and authorize integrations, Caddy standard modules, and
caddy-trace.
For the independently installable cmd/caddy-authenticator, use the
standalone authenticator reference. It owns
profile-based portal login, private credentials/token/log storage, and the
command's user guide. Its implementation reuses go-authcrunch/pkg/authclient;
it does not load Caddy server modules or require the portal admin API.
Use release-and-versioning to maintain version authority, release targets, release CI, packaging, and publication. After changing commands, scripts, CI, build behavior, or selected dependencies, review and update the affected repo-local skills and references in the same change. Follow keeping skills current so documented commands, side effects, prerequisites, and validation match the resulting workflow.
Prefer narrow go test commands for quick validation while editing. Use the
Makefile targets when the user asks for the repository workflow, reports,
release preparation, fixture formatting, or CI-like behavior.
Follow the repository scope,
including its sole exception for ../xcaddy-caddy-security. Inspect working
directories, script side effects, cleanup paths, and output overrides before
execution. Run this module's automation; sibling source-module build, test,
formatting, license, dependency, and cleanup workflows remain out of scope.
go test ./... for a fast all-package check without coverage reports.go test -run <TestName> ./... for focused validation.make build to validate VERSION and the authenticator fallback, compile
cmd/authcrunch and cmd/caddy-authenticator into their corresponding bin/
executables with -mod=readonly -trimpath, and print both versions. It injects
VERSION into the authenticator's main.appVersion linker variable.make when the user asks for the default build; it runs info and
build.make test for uncached, race-enabled Go tests and complete reports
through pinned go tool tested and the resource guard. TEST is a regex,
TEST_DIR accepts package patterns, and TEST_TIMEOUT is a quoted per-package duration (default 60m).
MINIMUM_COVERAGE=1 checks for nonzero coverage; it is not a coverage goal.
Read test resource controls for concurrency,
memory, wall-time limits, cancellation, live output and resource evidence.make qtest for the root package (.) by default, or set
QUICK_TEST_DIR and TEST for another scope. Reports go to .coverage/quick.make run-reports to rebuild presentations from recorded tested evidence.
It preserves failure status. make coverage is an alias for this operation;
it does not rerun tests.make test-automation for verbose Python fixture tests of artifact
identity, build metadata, and the real Make/tested lifecycle.make scan-codeql for a local Go scan, or set CODEQL_LANGUAGE to
javascript-typescript, python or actions for the other CI languages.
Use make test-codeql for real CLI regression fixtures in the selected
language. Read the
CodeQL workflow for CLI prerequisites, evidence,
approved suppression policy, and findings review.make oidc-conformance-prepare and make oidc-conformance-test for the opt-in
official Foundation plans against a fresh Caddy binary. Follow the
conformance workflow
for pinned local prerequisites, private evidence, strict TLS trust and
preserved nonzero results. Conformance units/E2E and their artifacts are
separate from regular testing; existing local OIDC regressions remain default.
Set CONFORMANCE_RESULTS to a new directory below this checkout's tmp/;
open its private index.html for explanations and links to all run evidence.
Missing downloaded prerequisites require make oidc-conformance-prepare.
Use make oidc-conformance-help for local tool locations and removal commands
that preserve result bundles; it does not install or remove anything.OIDC conformance Actions workflow for a downloadable
report from a hosted runner. Its setup and artifact reference
explains the readable summary, complete report after one ZIP extraction,
original runner status and failed-run uploads. This never joins regular CI.make oidc-conformance-cleanup to remove all identified OIDC result
bundles under tmp/, including custom destinations and top-level supplemental
oidc-* logs, audits and browser reports, plus audit_oidc_*.py/check_oidc_*.py
helpers. Reserve these temporary names for generated OIDC output; prefer
keeping new diagnostics inside their run bundle. Cleanup retains the prepared
workspace, dependencies and caches, records custom dependency locations for
repeated cleanup, and refuses active runs/preparation. It does not clean
ordinary .coverage/ or unrelated temporary files. See the
cleanup scope.make ci-check for sequential version, automation, full Go test/report,
and build gates, including under make -j.make version-check for read-only version validation and
make artifact-id for version/timestamp/commit identity and CI outputs.
After an explicit VERSION edit, make version-sync updates the authenticator's
Go install fallback without bumping or staging a release.make fmtcfg to format Caddyfile fixtures under
testdata/caddyfile_adapt and assets/config; it requires an existing
bin/authcrunch.make clean only when cleanup is requested; it removes generated
.coverage/ and bin/ directories.If documentation mentions make ctest, treat it as stale in this repository and
choose make test, make qtest, or direct go test instead.
Read the module's Go minimum and Caddy dependency from go.mod; inspect
Makefile separately for the Caddy version used by devbuild. CI explicitly
selects Go 1.26.8 with GOTOOLCHAIN=local and Node 24; Python 3.9+ runs
automation. The default Go suite requires Chrome/Chromium for Caddy browser
refresh E2E. Set AUTHCRUNCH_TEST_BROWSER when autodetection cannot find the
executable. Missing browser/Node prerequisites fail the test; no sibling UI
build or npm dependency installation is needed. See
browser validation.
go.mod and go.sum pin github.com/greenpau/tested v1.1.0 and the release tool
github.com/greenpau/versioned/cmd/versioned; use go tool tested and
go tool versioned. make dep downloads/verifies module
dependencies and resolves tested. make install-test-tools runs its version
command without global installs or module edits. The other maintenance tools,
such as xcaddy for devbuild and versioned for the license
recipes, must already be on PATH; make dep does not install them.
make license selects tracked and nonignored new Go files through Git. It must
not traverse ignored tmp/, suite checkouts, tool caches or vendored modules;
rewriting those files would invalidate the unmodified dependency evidence.
Module/tool downloads and xcaddy can need network access. Tests and builds
do not run module tidy, license rewrites, download-link regeneration, or
Caddyfile formatting. Use explicit maintenance targets when those changes are
intended.
make devbuild uses the explicitly permitted ../xcaddy-caddy-security
workspace. It removes files there, changes into that directory, and runs
xcaddy to build Caddy with this module, the static secrets manager,
caddy-trace, and a local go-authcrunch replacement. The final binary is
bin/authcrunch in this repository.
Use this target when an integrated xcaddy build is needed. Check the actual
workspace and cleanup paths before running it, including whether a symlink
redirects them. The exception is limited to ../xcaddy-caddy-security;
overriding PLUGIN_NAME must not redirect writes to another sibling. The
Makefile hard-codes the go-authcrunch replacement path in a --with ...=...
argument; verify it selects the intended existing checkout, and keep that
checkout read-only. Use make build when the normal Caddy wrapper meets the
task.
For an explicitly requested published version, use a targeted upgrade from this
repository: go get github.com/greenpau/go-authcrunch@<requested-version>, then
go mod tidy and go mod verify. Inspect the dependency diff and keep the
versioned replacement examples in CONTRIBUTING.md and the xcaddy argument in
Makefile aligned. Do not use make upgrade for a single-module request: it
updates all dependencies. make sync takes its version from the sibling's
VERSION, which may differ from the requested release. Confirm the selected
module's Dir and absence of an unintended Replace before validation.
For official OIDC qualification of newer committed work, select its exact
published commit with go get github.com/greenpau/go-authcrunch@<commit>.
The resulting immutable pseudo-version must match the intended sibling revision;
the conformance harness rejects local replacements. Record the selected module
checksum and origin, and keep sibling source and Git state read-only.
Development in caddy-security often connects this module to a local
github.com/greenpau/go-authcrunch checkout that sits next to the
caddy-security directory in the filesystem tree. If caddy-security is at
<parent>/caddy-security, assume go-authcrunch is at
<parent>/go-authcrunch; from this repository, that path is
../go-authcrunch.
Use a Go module replacement when the task requires consuming existing local
go-authcrunch changes. Edit only this repository's go.mod and validate this
module; do not develop, format, tidy, or test the sibling checkout. Read the
currently required go-authcrunch version from this repository's go.mod:
go list -m -f '{{.Version}}' github.com/greenpau/go-authcrunchThen use that required version in the replacement command:
go mod edit -replace github.com/greenpau/go-authcrunch@<go-authcrunch-version-from-go.mod>=../go-authcrunchKeep the replacement while this module intentionally depends on existing
unreleased upstream changes. Upstream implementation and publication happen
as separate work. Once the required version is available, update this
repository's dependency, remove its local replacement, and test here.
make sync removes local go-authcrunch replacements after updating references;
it must not be used as a reason to edit or release the sibling first.
After changing the selected Caddy or go-authcrunch version, audit delegated Caddyfile grammar and examples using Syntax maintenance. A dependency update can change accepted directives even when no local parser switch changes. Refresh the owning configuration skills and syntax comments.
assets/scripts/generate_downloads.sh rewrites Caddy download links in
README.md. See release-and-versioning
for version inputs and regeneration requirements. It is called by
make release, make minor-release, their fast- variants, and make license.
assets/scripts/update_doc_refs.sh reads ../go-authcrunch/VERSION, updates
go-authcrunch references in CONTRIBUTING.md, Makefile, and go.mod, removes
local go-authcrunch replace directives from go.mod, then runs go mod tidy,
go mod verify, make, and make test. make sync invokes this script.
Use make sync only for an explicit go-authcrunch reference refresh. The script
assumes a sibling ../go-authcrunch checkout and uses BSD/macOS sed -i ''
syntax. The sibling VERSION is an input only; all reference updates, module
commands, builds, and tests run in caddy-security.
make upgrade runs go get -u ./... and go mod tidy; use it only for an
explicit dependency upgrade.make license applies the repository license header to every Go file with
versioned and regenerates download links; expect broad source changes.make logo requires GraphicsMagick gm and rewrites
assets/docs/images/logo.png.make linter is currently a placeholder and does not run golint.Do not treat generated outputs as source changes unless the user explicitly asks to update or commit them.
bin/authcrunch is produced by build/devbuild targets; make build also
produces bin/caddy-authenticator..coverage/ contains the tested HTML/JSON/JUnit reports, raw test output,
coverage profile, stderr, run metadata, and generation manifest. Start at
.coverage/index.html; see testing-and-ci for the complete evidence layout..coverage/codeql/ holds local scan databases, raw and reviewed SARIF/CSV,
suppression audits, logs, and retained regression fixtures.
Its evidence is separate from tested's report bundle;
make clean removes both. Local CodeQL does not upload or dismiss alerts.../xcaddy-caddy-security is the permitted devbuild workspace. Only that
sibling workspace may be created, refreshed, or cleaned for xcaddy builds.Formatted Caddyfiles, README download links, VERSION, go.mod, and
go.sum can be intentional source changes depending on the target. Review the
diff before deciding whether to keep them.
COVERAGE_DIR selects the report directory. Keep overrides inside this checkout;
guarded runs in one checkout are serialized by .coverage/test-resource.lock,
even when output directories differ. Keep this lock in place during validation.
Let tested refresh only its managed artifacts: do not recursively delete report
directories in test targets. Full, quick, and custom bundles and unrelated investigation files must
survive one another's runs.
Whole-directory cleanup belongs to the explicitly requested make clean.
Normal coverage reports include the root test executable's E2E subprocesses through Go's native coverage merge. See subprocess coverage for the bootstrap, regression tests and limits. Keep merging before tested evaluates coverage and writes reports; never patch a finished bundle's coverage percentage.
The reusable .github/workflows/build.yml runs make dep and make ci-check,
checks source remains unchanged, and uploads the complete .coverage/ bundle
after an attempted gate, including failure evidence. Release CI requires this
same gate. The testing contract owns local
reproduction; release ownership covers
artifact identities and tag requirements.
The CLA workflow may update assets/cla/signatures.json through GitHub
automation. Do not edit CLA signatures or consent files unless the user asks.
Run bin/authcrunch security version to print the go-authcrunch module linked
into the executable, for example go-authcrunch v1.2.6. This uses
runtime/debug.ReadBuildInfo and works without a config, server, credentials,
Go installation or source checkout. Do not substitute the caddy-security
VERSION, a working-directory go.mod, or the authdb package's version banner.
bin/authcrunch version continues to report Caddy's version.
Preserve pseudo-versions and module replacements in diagnostics. A replacement
prints go-authcrunch <required-version> => <replacement-path> <replacement-version>;
an unversioned local replacement uses (devel), so the required release is not
mistaken for the actual checkout. Missing build metadata prints
go-authcrunch unknown. command_security.go owns registration and formatting;
its unit tests and TestCaddySecurityVersionE2E cover the command contract.
The built binary registers the security command group through Caddy's command
extension API. It is separate from adapt, validate, run, reload, and Make maintenance.
Use nested command words for the domain, action, and resource, such as
bin/authcrunch security oauth create application. Follow this pattern for future
security commands.
Use oauth init provisioning store for storage of OAuth application credentials and
OIDC provider signing keys; reserve user-registration terminology for user sign-up.
Use Private provisioning and activation
for the private input grammar and oauth init provisioning store,
oauth create application, oauth rotate secret, and oidc create signing key
subcommands, explicit revision activation, and interrupted-writer recovery.
Each provisioning command prints only the resulting path; it never prints client
secrets or private keys.
Use Local user commands for
security local client configuration, login, local realm/user inspection,
account creation/deletion, password resets, roles/challenges, realm reload,
and offline password/API-key generation. Remote operations use the portal's
admin API; generators work offline and never modify database files.
© greenpau, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (references) in .codex/skills/scripts-and-automation of greenpau/caddy-security.
Open the folder on GitHubat commit a48553d
Scripts And Automation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Scripts And Automation this skillgreenpau/caddy-security | 2.3k | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| LangBot EBA Adapter Developmentlangbot-app/LangBot | 18k | — | ~4k | Automated safety check: Pass | Apache-2.0 | |
| Aqua Communicationquailyquaily/aqua | 258 | 1 repos | ~4.7k | Automated safety check: Notes | Apache-2.0 | |
| Himalaya Email CLIPrismer-AI/PrismerCloud | 1.6k | 3 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Wp Performancegambitph/Stackable | 350 | 3 repos | ~1.5k | Automated safety check: Pass | GPL-3.0 | |
| Trigger.dev Background Taskspapermark/papermark | 9.2k | — | ~2.1k | Automated safety check: Pass | Custom licence |
langbot-app/LangBot
Guides building, migrating and testing LangBot messaging-platform adapters for the Event-Based Agents layout, with unified event and message conversion.
quailyquaily/aqua
Aqua is a CLI-first message tool for AI agents. An agent skill from quailyquaily/aqua.
Prismer-AI/PrismerCloud
Operates a mailbox from the terminal with the external Himalaya CLI over IMAP, SMTP, Notmuch or Sendmail, separate from any built-in email gateway adapter.
gambitph/Stackable
A skill your agent uses when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers)…
papermark/papermark
Guides building durable background tasks, scheduled jobs and queues with Trigger.dev, including retries, waits, idempotency and concurrency limits.
gokapso/agent-skills
Connect WhatsApp to your product with Kapso: onboard customers with setup links, detect connections, receive events via webhooks, and send messages/templates/media.
greenpau/caddy-security
Build or troubleshoot portal JSON/native login clients, refresh, profile and admin APIs, and public JWKS.
greenpau/caddy-security
Implement or review caddy-security Go code, Caddy modules, parsers, lifecycle, and HTTP delegation.
greenpau/caddy-security
Build or review caddy-security Caddyfiles and select focused configuration skills.
greenpau/caddy-security
Configure portal/policy JWT keys, token names and lifetimes, key loading and generation, public-key discovery, and System API encryption keys.
greenpau/caddy-security
Mount authenticate and authorize handlers, separate portal and protected routes, align auth URLs, and preserve trusted proxy metadata.
greenpau/caddy-security
Configure durable AuthCrunch runtime state, exclusive storage ownership, stop/start persistence, reload rejection, and recovery.
Categories
Choose or maintain repository Make/script workflows, builds, dependency selection, generated artifacts, and security CLI tools. Scripts And Automation is an agent skill from greenpau/caddy-security. Choose or maintain repository Make/script workflows, builds, dependency selection, generated artifacts, and security CLI tools.
Scripts And Automation fits situations like: backend & APIs work in your project.
Run `npx skills add greenpau/caddy-security --skill scripts-and-automation -a claude-code`. Or copy the skill folder (.codex/skills/scripts-and-automation in greenpau/caddy-security) into .claude/skills/scripts-and-automation in your project. Claude Code loads it when a task matches its description.
Run `npx skills add greenpau/caddy-security --skill scripts-and-automation -a codex`. Or copy the skill folder (.codex/skills/scripts-and-automation in greenpau/caddy-security) into .agents/skills/scripts-and-automation in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add greenpau/caddy-security --skill scripts-and-automation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scripts-and-automation, .gemini/skills/scripts-and-automation, .github/skills/scripts-and-automation and .opencode/skills/scripts-and-automation in your project.
Going by SKILL.md and its folder, Scripts And Automation needs the command-line tools its instructions call (make and go). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Scripts And Automation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.9k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Scripts And Automation: LangBot EBA Adapter Development (langbot-app/LangBot, 18k stars), Aqua Communication (quailyquaily/aqua, 258 stars), Himalaya Email CLI (Prismer-AI/PrismerCloud, 1.6k stars) and Wp Performance (gambitph/Stackable, 350 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
greenpau (a GitHub user) maintains it in greenpau/caddy-security, which has 2,251 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 5, 2026.
Source: greenpau/caddy-security on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.