Audit Exception Safety
ben-manes/caffeine
Audit exception safety and failure atomicity across all throw sites
Runs task pipeline:check-exceptions to confirm every rule listed in repo-operation-pipeline.md's "Known exceptions" section as needing no script/task/skill/CI layer still genuinely has none.
$ npx skills add agntcy/coffeeAgntcy --skill auditing-pipeline-exceptions -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agntcy/coffeeAgntcy auditing-pipeline-exceptions --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/agntcy/coffeeAgntcy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/quality-checks/auditing-pipeline-exceptions .claude/skills/auditing-pipeline-exceptions && 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 "auditing-pipeline-exceptions" agent skill from https://github.com/agntcy/coffeeAgntcy/tree/main/.agents/skills/quality-checks/auditing-pipeline-exceptions into .claude/skills/auditing-pipeline-exceptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auditing-pipeline-exceptions", 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/agntcy/coffeeAgntcy/tree/main/.agents/skills/quality-checks/auditing-pipeline-exceptionsType 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 agntcy/coffeeAgntcy --skill auditing-pipeline-exceptions -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agntcy/coffeeAgntcy auditing-pipeline-exceptions --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agntcy/coffeeAgntcy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/quality-checks/auditing-pipeline-exceptions .agents/skills/auditing-pipeline-exceptions && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "auditing-pipeline-exceptions" agent skill from https://github.com/agntcy/coffeeAgntcy/tree/main/.agents/skills/quality-checks/auditing-pipeline-exceptions into .agents/skills/auditing-pipeline-exceptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auditing-pipeline-exceptions", 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 agntcy/coffeeAgntcy --skill auditing-pipeline-exceptions -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agntcy/coffeeAgntcy auditing-pipeline-exceptions --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agntcy/coffeeAgntcy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/quality-checks/auditing-pipeline-exceptions .cursor/skills/auditing-pipeline-exceptions && 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 "auditing-pipeline-exceptions" agent skill from https://github.com/agntcy/coffeeAgntcy/tree/main/.agents/skills/quality-checks/auditing-pipeline-exceptions into .cursor/skills/auditing-pipeline-exceptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auditing-pipeline-exceptions", 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/agntcy/coffeeAgntcy.git --path .agents/skills/quality-checks/auditing-pipeline-exceptions--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 agntcy/coffeeAgntcy --skill auditing-pipeline-exceptions -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agntcy/coffeeAgntcy auditing-pipeline-exceptions --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agntcy/coffeeAgntcy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/quality-checks/auditing-pipeline-exceptions .gemini/skills/auditing-pipeline-exceptions && 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 "auditing-pipeline-exceptions" agent skill from https://github.com/agntcy/coffeeAgntcy/tree/main/.agents/skills/quality-checks/auditing-pipeline-exceptions into .gemini/skills/auditing-pipeline-exceptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auditing-pipeline-exceptions", 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 agntcy/coffeeAgntcy auditing-pipeline-exceptionsInstalls 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 agntcy/coffeeAgntcy --skill auditing-pipeline-exceptions -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agntcy/coffeeAgntcy.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/quality-checks/auditing-pipeline-exceptions .github/skills/auditing-pipeline-exceptions && 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 "auditing-pipeline-exceptions" agent skill from https://github.com/agntcy/coffeeAgntcy/tree/main/.agents/skills/quality-checks/auditing-pipeline-exceptions into .github/skills/auditing-pipeline-exceptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auditing-pipeline-exceptions", 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 agntcy/coffeeAgntcy --skill auditing-pipeline-exceptions -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agntcy/coffeeAgntcy auditing-pipeline-exceptions --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agntcy/coffeeAgntcy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/quality-checks/auditing-pipeline-exceptions .opencode/skills/auditing-pipeline-exceptions && 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 "auditing-pipeline-exceptions" agent skill from https://github.com/agntcy/coffeeAgntcy/tree/main/.agents/skills/quality-checks/auditing-pipeline-exceptions into .opencode/skills/auditing-pipeline-exceptions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "auditing-pipeline-exceptions", 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.
auditing-pipeline-exceptionsRuns task pipeline:check-exceptions to confirm every rule listed in repo-operation-pipeline.md's "Known exceptions" section as needing no script/task/skill/CI layer still genuinely has none.
Auditing Pipeline Exceptions is an agent skill from agntcy/coffeeAgntcy. Runs task pipeline:check-exceptions to confirm every rule listed in repo-operation-pipeline.md's "Known exceptions" section as needing no script/task/skill/CI layer still genuinely has none. Use before finishing a change that adds a skill, or when asked to audit the pipeline rule's exception list.
Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: End-to-end reference application for AGNTCY Components. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit 1dbe6c5. 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.
No scripts in the folder and no shell commands in SKILL.md.
From 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.
Auditing Pipeline Exceptions loads about 681 tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 191 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 agntcy/coffeeAgntcy at commit 1dbe6c5, republished under its Apache-2.0 licence (© agntcy). 191 words, ~681 tokens.
.claude/skills/auditing-pipeline-exceptions/SKILL.md (or your agent's skills folder).Runs task pipeline:check-exceptions (defined in
Taskfile.yaml, wrapping
scripts/checks/check_pipeline_exceptions.bash)
to check every rule listed in
.agents/rules/meta/repo-operation-pipeline.md's
"Known exceptions" section (the "purely manual/visual conventions"
bucket - no script/task/skill/CI layer at all) for a skill that's since
grown into being that rule's own entry point without the rule being
promoted out of the list. This is the same check task check:all runs
as part of checks.yaml. See
.agents/rules/meta/repo-operation-pipeline.md
for the underlying rule.
- [ ] 1. Run: task pipeline:check-exceptions
- [ ] 2. If it fails, it names the rule now in violation: either promote
that rule out of the exception list (give it the script/task/
skill/CI layers repo-operation-pipeline.md's main pattern
describes, via the add-repo-operation skill), or, if the flagged
skill's cross-link was a mistake (it named that rule as its
"underlying rule" without actually being built for it), fix the
skill's own cross-link instead
- [ ] 3. Re-run task pipeline:check-exceptions to confirm it's cleanSKILL.md, not just any mention of that filename anywhere. A skill
can legitimately mention an exception-listed rule in passing (e.g.
add-repo-operation tells agents to also apply
alphabetize-entity-lists.md and pre-finalize-checks.md while
adding an operation) without being that rule's own entry point - only
the "underlying rule" cross-link means a skill was actually built for
it.repo-operation-pipeline.md (CI-only orchestration, bootstrap tooling
itself, one-shot generative actions, a genuinely different execution
model) each assert something different and aren't covered by this
check.© agntcy, 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
Just SKILL.md in .agents/skills/quality-checks/auditing-pipeline-exceptions of agntcy/coffeeAgntcy.
Open the folder on GitHubat commit 1dbe6c5
Auditing Pipeline Exceptions 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 |
|---|---|---|---|---|---|---|
| Auditing Pipeline Exceptions this skillagntcy/coffeeAgntcy | 112 | — | ~681 | Automated safety check: Pass | Apache-2.0 | |
| Audit Exception Safetyben-manes/caffeine | 18k | — | ~633 | Automated safety check: Pass | Apache-2.0 | |
| Codex Rules Referencecode-yeongyu/oh-my-openagent | 70k | — | ~269 | Automated safety check: Pass | Custom licence | |
| Production Auditaffaan-m/ECC | 276k | 1 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Aims Auditalirezarezvani/claude-skills | 28k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Geo Auditsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.4k | Automated safety check: Notes | MIT |
ben-manes/caffeine
Audit exception safety and failure atomicity across all throw sites
code-yeongyu/oh-my-openagent
Explains how the Codex Rules plugin injects project instructions and file-specific rules into a session, which rule files it reads and which settings control it.
affaan-m/ECC
Local-evidence production readiness audit for shipped apps, pre-launch reviews, post-merge checks, and "what breaks in prod?" questions without sending repo data to an external audit service.
alirezarezvani/claude-skills
/cs:aims-audit <scope — ISO/IEC 42001 AIMS internal-audit 6-question forcing interrogation.
sickn33/agentic-awesome-skills
Full website GEO+SEO audit with parallel subagent delegation.
diegosouzapw/OmniRoute
Command reference for omniroute's audit, logs, policy and telemetry commands: search and export audit trails, manage access policies and review request history for compliance work.
agntcy/coffeeAgntcy
A skill your agent uses when the user asks about A2A (Agent-to-Agent) protocol communication, OASF record formats, AGNTCY directory operations, agent card parsing, or dirctl CLI usage.
agntcy/coffeeAgntcy
Guides adding a new repository operation (a check, validation, or piece of tooling) through this repo's standard script - Taskfile task - skill - CI enforcement - rule pipeline.
agntcy/coffeeAgntcy
Authors and maintains the human-facing Agentic Workflows API documentation for the lungo subproject at coffeeAGNTCY/coffeeagents/lungo/docs/workflow-instanceapi.md.
agntcy/coffeeAgntcy
Checks whether any Helm chart under coffeeAGNTCY/coffeeagents/{corto,lungo}/deployment/helm// has content changes not covered by a later Chart.yaml version: bump, anywhere in that chart's history…
agntcy/coffeeAgntcy
Runs task pins:check to find any third-party GitHub Action, reusable-workflow, or image reference that isn't pinned to an immutable SHA/digest, and pins each one it finds.
agntcy/coffeeAgntcy
Runs task workflows:check-permissions to find any GitHub Actions workflow file with a write-all grant or no declared permissions, and scopes it down to least privilege.
Runs task pipeline:check-exceptions to confirm every rule listed in repo-operation-pipeline.md's "Known exceptions" section as needing no script/task/skill/CI layer still genuinely has none. Auditing Pipeline Exceptions is an agent skill from agntcy/coffeeAgntcy.md's "Known exceptions" section as needing no script/task/skill/CI layer still genuinely has none.
Run `npx skills add agntcy/coffeeAgntcy --skill auditing-pipeline-exceptions -a claude-code`. Or copy the skill folder (.agents/skills/quality-checks/auditing-pipeline-exceptions in agntcy/coffeeAgntcy) into .claude/skills/auditing-pipeline-exceptions in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agntcy/coffeeAgntcy --skill auditing-pipeline-exceptions -a codex`. Or copy the skill folder (.agents/skills/quality-checks/auditing-pipeline-exceptions in agntcy/coffeeAgntcy) into .agents/skills/auditing-pipeline-exceptions 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 agntcy/coffeeAgntcy --skill auditing-pipeline-exceptions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auditing-pipeline-exceptions, .gemini/skills/auditing-pipeline-exceptions, .github/skills/auditing-pipeline-exceptions and .opencode/skills/auditing-pipeline-exceptions in your project.
SKILL.md names no scripts, command-line tools or credentials: Auditing Pipeline Exceptions is instructions for the agent only.
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.
Auditing Pipeline Exceptions 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 681 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Auditing Pipeline Exceptions: Audit Exception Safety (ben-manes/caffeine, 18k stars), Codex Rules Reference (code-yeongyu/oh-my-openagent, 70k stars), Production Audit (affaan-m/ECC, 276k stars) and Aims Audit (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agntcy (a GitHub organization) maintains it in agntcy/coffeeAgntcy, which has 112 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 9, 2026.
Source: agntcy/coffeeAgntcy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.