Code Patterns
Aedelon/claude-code-blueprint
Reference patterns for REST APIs, pytest/vitest testing, Docker multi-stage builds, GitHub Actions CI/CD, PostgreSQL, TypeScript generics, Python async, and React Server Components.
Flags irreversible decisions before commit. An agent skill from jamditis/claude-skills-journalism.
$ npx skills add jamditis/claude-skills-journalism --skill one-way-door -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jamditis/claude-skills-journalism one-way-door --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/jamditis/claude-skills-journalism.git skills-src && mkdir -p .claude/skills && cp -r skills-src/dev-toolkit/skills/one-way-door .claude/skills/one-way-door && 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 "one-way-door" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/one-way-door into .claude/skills/one-way-door/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-way-door", 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/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/one-way-doorType 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 jamditis/claude-skills-journalism --skill one-way-door -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jamditis/claude-skills-journalism one-way-door --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .agents/skills && cp -r skills-src/dev-toolkit/skills/one-way-door .agents/skills/one-way-door && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "one-way-door" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/one-way-door into .agents/skills/one-way-door/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-way-door", 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 jamditis/claude-skills-journalism --skill one-way-door -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jamditis/claude-skills-journalism one-way-door --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/dev-toolkit/skills/one-way-door .cursor/skills/one-way-door && 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 "one-way-door" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/one-way-door into .cursor/skills/one-way-door/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-way-door", 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/jamditis/claude-skills-journalism.git --path dev-toolkit/skills/one-way-door--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 jamditis/claude-skills-journalism --skill one-way-door -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jamditis/claude-skills-journalism one-way-door --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/dev-toolkit/skills/one-way-door .gemini/skills/one-way-door && 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 "one-way-door" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/one-way-door into .gemini/skills/one-way-door/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-way-door", 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 jamditis/claude-skills-journalism one-way-doorInstalls 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 jamditis/claude-skills-journalism --skill one-way-door -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .github/skills && cp -r skills-src/dev-toolkit/skills/one-way-door .github/skills/one-way-door && 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 "one-way-door" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/one-way-door into .github/skills/one-way-door/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-way-door", 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 jamditis/claude-skills-journalism --skill one-way-door -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jamditis/claude-skills-journalism one-way-door --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/dev-toolkit/skills/one-way-door .opencode/skills/one-way-door && 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 "one-way-door" agent skill from https://github.com/jamditis/claude-skills-journalism/tree/master/dev-toolkit/skills/one-way-door into .opencode/skills/one-way-door/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "one-way-door", 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.
one-way-doorFlags irreversible decisions before commit. An agent skill from jamditis/claude-skills-journalism.
One Way Door is an agent skill from jamditis/claude-skills-journalism. Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.
Its SKILL.md is about 5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `agents/openai.yaml`).
It sits in DevOps & Cloud, covering API design and CI/CD. It works with Kubernetes. The repository describes itself as: Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e3e2172. 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.
Ships script files (PowerShell), which the agent can run.
Shell commands in SKILL.md call:
tsxterraformpulumiFrom 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.
One Way Door loads about 5k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 1,545 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 noted patterns worth knowing about, such as sudo or a known installer.
- **Configuration files**, `.env`, feature flags, app configAutomated 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 jamditis/claude-skills-journalism at commit e3e2172, republished under its MIT licence (© jamditis). 1,545 words, ~5,028 tokens.
.claude/skills/one-way-door/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Some decisions are easy to reverse, you can change a UI component, rename a variable, or swap a utility function with no lasting consequences. These are two-way doors: walk through, and if it's wrong, walk back.
Other decisions create gravity. Once traffic, users, or other code depends on them, changing course gets expensive. A database schema migration after launch. An API contract that external consumers rely on. An auth boundary that shapes your entire permission model. These are one-way doors.
The most expensive mistakes in software aren't bugs. They're irreversible architectural decisions made too quickly.
Files matching: schema.prisma, schema.graphql, *.sql, migration*, models.py, models.ts, entities.py, entities.ts
Data models are the hardest decisions to reverse. Once your database has rows, every schema change requires a migration. Column renames break queries. Relationship changes cascade through your entire application.
Questions to ask:
Files matching: docker-compose*, Dockerfile, *.tf, terraform*, pulumi*, cdk*, cloudformation*, k8s*, kubernetes*, helm*
Infrastructure choices constrain everything built on top of them. Switching from ECS to Kubernetes, or from Lambda to containers, affects deployment pipelines, monitoring, scaling, and team knowledge.
Questions to ask:
Files matching: auth.{ts,js,py}, firestore.rules, storage.rules, *.rules, security.{ts,js,py,json,rules,yaml,yml}, rbac.{ts,js,py,json}, permissions.{ts,js,py,json}
These patterns are extension-qualified on purpose: an unrelated file that merely contains the word security or permissions (a note, a doc, a test) does not trip the check.
Auth boundaries are load-bearing walls. Session vs JWT, role-based vs attribute-based, single-tenant vs multi-tenant, each choice shapes your security model, user experience, and compliance posture.
Questions to ask:
Files matching: openapi*, swagger*, *.proto, *.graphql, api-schema*, routes.ts, routes.js, routes.py
Published APIs are promises to consumers. Breaking changes require versioning, deprecation periods, and migration guides. Internal APIs between services create coupling that's hard to unwind.
Questions to ask:
Files matching: events.ts, eventbus.ts, eventemitter.py, eventhandler.py, pubsub*, queue*, kafka*, rabbit*
Event schemas are contracts between producers and consumers. Once multiple services subscribe to an event, changing its shape requires coordinated deploys. Event ordering assumptions become architectural constraints.
Questions to ask:
Files in: .github/, .gitlab/, .circleci/, or matching Jenkinsfile, .travis.yml, cloudbuild*
CI/CD pipelines become the backbone of your release process. Teams build muscle memory around deploy workflows. Changing pipeline structure means retraining, and broken deploys during the transition can block your entire team.
Questions to ask:
Files matching: package.json, Cargo.toml, go.mod, requirements.txt, pyproject.toml, Gemfile
Framework and dependency choices ripple through your entire codebase. Switching from React to Vue, or from Express to Fastify, means rewriting large portions of your application.
Questions to ask:
Files matching: firebase.json, .firebaserc, firestore.indexes*
Cloud service configs lock you into specific providers and architectures. Firestore indexes determine query performance. Firebase rules define your security boundary.
Questions to ask:
These file types are safe to decide quickly and change later:
.env, feature flags, app configThe CLAUDE.md rule leans on judgement, but the automated hook hard-codes an early-exit safelist that runs before any pattern check. These classes always pass, even when the filename contains a keyword like auth or security, because they're the common false positives:
test_*.py, *_test.py, *.test.{ts,tsx,js,jsx}, *.spec.{ts,tsx,js,jsx}tests/, __tests__/, fixtures/, mocks/, or __mocks__/ directory*.md)*.txt / *.rst under a plans/, docs/, notes/, or superpowers directoryAdd this to your project's CLAUDE.md:
### One-way door check
Before creating new files that represent architectural decisions, ask: "Which of these decisions would be difficult to reverse?" One-way doors include data models, service communication patterns, auth boundaries, tenancy models, and infrastructure configs. These create gravity, once traffic, users, or other code depends on them, changing course gets expensive. If a decision is a one-way door, pause and discuss the trade-offs before committing. Two-way doors (UI components, utilities, styling) can be decided quickly and changed later.The automated version is two hooks that share a session-scoped approval ledger:
one-way-door-check.sh runs on PreToolUse:Write. It blocks the first write to a one-way-door file and records that file as pending.one-way-door-approve.sh runs on PostToolUse:AskUserQuestion. When you answer any AskUserQuestion, normally the one the check told Claude to ask, it promotes every pending file to approved, so Claude's retried write passes.Without the ledger the check would be stateless and re-block the same file on every retry, the "use AskUserQuestion, then retry" instruction would loop forever. The ledger makes the loop terminate: answer once, and every file currently pending, usually just the one the check told Claude to ask about, stays open for the rest of the session. A one-way-door file you have not tried to write yet is not pending, so it still blocks the first time Claude attempts it.
The promoter keys on the AskUserQuestion event itself, not on which question was answered: it approves the whole pending set at once, so if two one-way-door files are blocked before Claude asks, or it asks an unrelated question while a file is pending, they are all approved together. The block-then-discuss prompt is the real guardrail; the ledger only keeps an already-discussed file from re-blocking.
Add both hooks to your Claude Code settings.json:
{
"hooks": {
"PreToolUse": [
{
"matcher": "Write",
"hooks": [
{
"type": "command",
"command": "/path/to/one-way-door-check.sh"
}
]
}
],
"PostToolUse": [
{
"matcher": "AskUserQuestion",
"hooks": [
{
"type": "command",
"command": "/path/to/one-way-door-approve.sh"
}
]
}
]
}
}one-way-door-check.sh)#!/bin/sh
# One-way door check hook (PreToolUse:Write)
# Flags architectural decisions that are hard to reverse.
# The most expensive mistakes aren't bugs, they're irreversible decisions.
INPUT=$(cat)
[ -z "$INPUT" ] && exit 0
# Extract the file path from tool_input
FILE_PATH=$(echo "$INPUT" | grep -oP '"file_path"\s*:\s*"[^"]*"' | head -1 | sed 's/.*"file_path"\s*:\s*"//;s/"//')
[ -z "$FILE_PATH" ] && exit 0
# Session-scoped approval ledger. Once the user approves a one-way-door file
# via the required AskUserQuestion, the PostToolUse:AskUserQuestion hook
# promotes it to approved, and subsequent writes to that same file proceed.
SESSION_ID=$(echo "$INPUT" | grep -oP '"session_id"\s*:\s*"[^"]*"' | head -1 | sed 's/.*"session_id"\s*:\s*"//;s/"//')
[ -z "$SESSION_ID" ] && SESSION_ID="default"
STATE_DIR="$HOME/.claude/hooks/state/one-way-door"
mkdir -p "$STATE_DIR"
APPROVED_FILE="$STATE_DIR/$SESSION_ID.approved"
PENDING_FILE="$STATE_DIR/$SESSION_ID.pending"
# Already approved this session: allow without re-blocking.
if [ -f "$APPROVED_FILE" ] && grep -Fxq "$FILE_PATH" "$APPROVED_FILE"; then
echo "one-way-door: proceeding with previously-approved $(basename "$FILE_PATH")" >&2
exit 0
fi
FILENAME=$(basename "$FILE_PATH")
FILENAME_LOWER=$(echo "$FILENAME" | tr "[:upper:]" "[:lower:]")
FILE_PATH_LOWER=$(echo "$FILE_PATH" | tr "[:upper:]" "[:lower:]")
DIR=$(dirname "$FILE_PATH")
# ---------------------------------------------------------------------------
# Early-exit safelist: clearly-additive, reversible file classes that should
# never trip a one-way-door check even if the filename contains a keyword like
# "auth" or "security". Tests and docs are the common false-positives.
# ---------------------------------------------------------------------------
# Test files (pytest, jest, vitest, go test conventions)
if echo "$FILENAME_LOWER" | grep -qE "^test_.*\.py$|_test\.py$|\.test\.(ts|tsx|js|jsx)$|\.spec\.(ts|tsx|js|jsx)$"; then
exit 0
fi
# Test / fixture / mock directories anywhere in the path
if echo "$FILE_PATH_LOWER" | grep -qE "/tests?/|/__tests__/|/fixtures?/|/mocks?/|/__mocks__/"; then
exit 0
fi
# Markdown is always reversible (broader than the later docs-only check, which
# required a docs/ parent dir and missed ad-hoc notes).
if echo "$FILENAME_LOWER" | grep -qE "\.md$"; then
exit 0
fi
ONE_WAY=0
REASON=""
# Documentation and plan files are always reversible - skip all checks
if echo "$FILENAME_LOWER" | grep -qE "\.txt$|\.rst$"; then
if echo "$DIR" | grep -qE "plans?|docs?|notes?|superpowers"; then
exit 0
fi
fi
# Database schemas and migrations
if echo "$FILENAME_LOWER" | grep -qE "schema\.(prisma|graphql|sql)|migration|\.sql$|models?\.(py|ts|js)$|entities?\.(py|ts|js)$"; then
ONE_WAY=1
REASON="data model / database schema"
fi
# Infrastructure and deployment configs
if echo "$FILENAME_LOWER" | grep -qE "^(docker-compose|dockerfile|terraform|pulumi|cdk)|\.tf$|cloudformation|k8s|kubernetes|helm"; then
ONE_WAY=1
REASON="infrastructure / deployment config"
fi
# Authentication and authorization (code/config files only - not docs)
if echo "$FILENAME_LOWER" | grep -qE "auth\.(ts|js|py)|firestore\.rules|storage\.rules|security\.(ts|js|py|json|rules|yaml|yml)|\.rules$|rbac\.(ts|js|py|json)|permissions\.(ts|js|py|json)"; then
ONE_WAY=1
REASON="auth / security rules"
fi
# API contracts and service interfaces
if echo "$FILENAME_LOWER" | grep -qE "openapi|swagger|\.proto$|\.graphql$|api-schema|routes\.(ts|js|py)$"; then
ONE_WAY=1
REASON="API contract / service interface"
fi
# Event systems and message queues
if echo "$FILENAME_LOWER" | grep -qE "event(s|bus|emitter|handler)\.(ts|js|py)$|pubsub|queue|kafka|rabbit"; then
ONE_WAY=1
REASON="event system / message bus"
fi
# Package manager configs (dependency choices)
if echo "$FILENAME_LOWER" | grep -qE "^(package\.json|cargo\.toml|go\.mod|requirements\.txt|pyproject\.toml|gemfile)$"; then
ONE_WAY=1
REASON="dependency / package config"
fi
# Firebase and cloud service configs
if echo "$FILENAME_LOWER" | grep -qE "^firebase\.json$|^\.firebaserc$|firestore\.indexes"; then
ONE_WAY=1
REASON="cloud service config (Firebase)"
fi
# CI/CD pipelines
if echo "$DIR" | grep -qE "\.(github|gitlab|circleci)" || echo "$FILENAME_LOWER" | grep -qE "^(jenkinsfile|\.travis\.yml|cloudbuild)"; then
ONE_WAY=1
REASON="CI/CD pipeline"
fi
if [ "$ONE_WAY" = "1" ]; then
# Record this file as pending approval for the session (deduped).
if [ ! -f "$PENDING_FILE" ] || ! grep -Fxq "$FILE_PATH" "$PENDING_FILE"; then
printf '%s\n' "$FILE_PATH" >> "$PENDING_FILE"
fi
cat >&2 <<HOOK_MSG
ONE_WAY_DOOR: You tried to create $FILENAME ($REASON). This write has been blocked because it is a one-way door -- a decision that becomes hard to reverse once other code, data, or users depend on it.
REQUIRED ACTION: You MUST use the AskUserQuestion tool before retrying this write. Present the user with:
1. What this file does and why it is a one-way door
2. At least 2 alternative approaches (if any exist) with their trade-offs
3. An option to proceed as planned
Frame the question around the specific architectural decision, not just "should I create this file?" The user needs to understand what they are committing to.
After the user answers the AskUserQuestion, retry the same write -- it will proceed automatically, because answering the question promotes this file to approved for the rest of the session. (Other unapproved one-way-door files still block.)
HOOK_MSG
exit 2
fi
exit 0one-way-door-approve.sh)#!/bin/sh
# One-way door approval promoter (PostToolUse:AskUserQuestion)
# When the user answers any AskUserQuestion, promote every one-way-door file
# that the PreToolUse:Write hook recorded as pending into the approved ledger
# for this session. The retried Write then passes instead of re-blocking.
# Never blocks: PostToolUse hooks must not interrupt the flow.
INPUT=$(cat)
[ -z "$INPUT" ] && exit 0
SESSION_ID=$(echo "$INPUT" | grep -oP '"session_id"\s*:\s*"[^"]*"' | head -1 | sed 's/.*"session_id"\s*:\s*"//;s/"//')
[ -z "$SESSION_ID" ] && SESSION_ID="default"
STATE_DIR="$HOME/.claude/hooks/state/one-way-door"
mkdir -p "$STATE_DIR"
APPROVED_FILE="$STATE_DIR/$SESSION_ID.approved"
PENDING_FILE="$STATE_DIR/$SESSION_ID.pending"
# Nothing pending: nothing to promote.
[ -s "$PENDING_FILE" ] || exit 0
# Promote each pending path into approved, deduped.
while IFS= read -r path; do
[ -z "$path" ] && continue
if [ ! -f "$APPROVED_FILE" ] || ! grep -Fxq "$path" "$APPROVED_FILE"; then
printf '%s\n' "$path" >> "$APPROVED_FILE"
fi
done < "$PENDING_FILE"
# Empty the pending list now that everything is approved.
: > "$PENDING_FILE"
exit 0How it works:
one-way-door-check.sh intercepts every Write (new file creation) and reads the file_path and session_id from the tool input..approved ledger, the write proceeds, the decision was already discussed this session. (The hook logs a one-line one-way-door: proceeding with previously-approved <file> note to stderr; it is not silent.).pending list, exits with code 2 (block), and tells Claude to use AskUserQuestion and then retry.AskUserQuestion, one-way-door-approve.sh (PostToolUse:AskUserQuestion) promotes every pending path into .approved and clears the pending list. It never blocks, PostToolUse hooks must not interrupt the flow.State:
The ledger lives in ~/.claude/hooks/state/one-way-door/, one pair of files per session: <session_id>.pending and <session_id>.approved. Approval is per file path, per session, a new session starts with an empty ledger, so the same decision is surfaced again rather than silently inherited from a past session. The key is the file path as Claude Code delivers it, which is normally absolute. If one session writes identically-named files through relative paths in different directories, the path key can collide and approve the second without its own discussion; wiring on absolute paths avoids that.
Exit codes:
0, Allow (two-way door, or a path already approved this session)2, Block (one-way door not yet approved, requires discussion)The shell scripts above assume a POSIX shell. On Windows, Claude Code invokes hooks through PowerShell, and tool_input.file_path can arrive with backslashes, which basename does not split on, so the shell version's safelist would misfire. Behavior-matched PowerShell ports ship alongside this skill:
one-way-door-check.ps1, the PreToolUse:Write checkone-way-door-approve.ps1, the PostToolUse:AskUserQuestion promoterThey use the same session ledger (%USERPROFILE%\.claude\hooks\state\one-way-door\), the same early-exit safelist, and the same one-way-door categories as the shell version. Filename and directory splitting goes through [System.IO.Path], and the directory patterns are matched after normalizing \ to /, so the check is correct whether a path uses backslashes or forward slashes. They mirror the shell hooks check-for-check, the same patterns in the same order, so the behavioral contract is identical; only the language differs.
Copy both .ps1 files from this skill's directory into your hooks folder (for example %USERPROFILE%\.claude\hooks\), then wire them with the PowerShell launcher. Update the command paths to match where you saved them (replace <you> with your username):
{
"hooks": {
"PreToolUse": [
{
"matcher": "Write",
"hooks": [
{
"type": "command",
"command": "powershell -ExecutionPolicy Bypass -File C:/Users/<you>/.claude/hooks/one-way-door-check.ps1"
}
]
}
],
"PostToolUse": [
{
"matcher": "AskUserQuestion",
"hooks": [
{
"type": "command",
"command": "powershell -ExecutionPolicy Bypass -File C:/Users/<you>/.claude/hooks/one-way-door-approve.ps1"
}
]
}
]
}
}Before committing to any one-way door, ask:
If you can't answer these questions clearly, you're not ready to walk through the door.
© jamditis, MIT. 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 3 other files in dev-toolkit/skills/one-way-door of jamditis/claude-skills-journalism.
Open the folder on GitHubat commit e3e2172
One Way Door 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 |
|---|---|---|---|---|---|---|
| One Way Door this skilljamditis/claude-skills-journalism | 416 | — | ~5k | Automated safety check: Notes | MIT | |
| Code PatternsAedelon/claude-code-blueprint | 120 | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| Cloud Infra Supply Chainzhaji2333/CkSKILLS | 115 | — | ~688 | Automated safety check: Warn | MIT | |
| Sap Btp Cloud Platformsecondsky/sap-skills | 462 | — | ~3.7k | Automated safety check: Pass | GPL-3.0 | |
| Apollo Deploy Integrationjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit | 260 | 6 repos | ~1.1k | Automated safety check: Notes | Custom licence |
Aedelon/claude-code-blueprint
Reference patterns for REST APIs, pytest/vitest testing, Docker multi-stage builds, GitHub Actions CI/CD, PostgreSQL, TypeScript generics, Python async, and React Server Components.
zhaji2333/CkSKILLS
当目标涉及云资产(对象存储/云元数据/Serverless)、容器/K8s、运维面板(宝塔/Grafana/Zabbix/Jenkins/GitLab/Nacos等)、消息队列/缓存中间件、CI/CD流水线、第三方回调集成、依赖组件CVE、信息泄露配置时调用。负责未授权访问、弱口令、云配置错误、供应链漏洞与敏感信息挖掘。
secondsky/sap-skills
Comprehensive SAP Business Technology Platform (BTP) reference for cloud development, deployment, and operations.
jeremylongshore/tons-of-skills-marketplace
Deploy Apollo.io integrations to production. An agent skill from jeremylongshore/tons-of-skills-marketplace.
maslennikov-ig/claude-code-orchestrator-kit
Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…
XiaomiMiMo/MiMo-Code
Runs OpenAI Codex CLI as a non-interactive worker for CI, Docker, Kubernetes or remote servers, with sandbox modes and JSONL-friendly output.
jamditis/claude-skills-journalism
A skill your agent uses when creating distinct website directions, a client review picker, asset catalog, previews, and Cloudflare-ready handoffs.
jamditis/claude-skills-journalism
Builds an Open Knowledge Format (OKF) knowledge base from existing docs, notes, or a repo.
jamditis/claude-skills-journalism
Local Gitleaks scans for staged changes, push ranges, and full history in private repos, with redacted reports.
jamditis/claude-skills-journalism
Acquire, clean, analyze, verify, visualize, and explain data for journalism.
jamditis/claude-skills-journalism
Creates print-ready HTML that exports to PDF. An agent skill from jamditis/claude-skills-journalism.
jamditis/claude-skills-journalism
Establishes how to find and use skills, requiring Skill tool invocation before any response.
Works with
Categories
Flags irreversible decisions before commit. An agent skill from jamditis/claude-skills-journalism. One Way Door is an agent skill from jamditis/claude-skills-journalism. Flags irreversible decisions before commit.
One Way Door fits situations like: auth boundaries; tasks that involve API design; tasks that involve CI/CD.
Run `npx skills add jamditis/claude-skills-journalism --skill one-way-door -a claude-code`. Or copy the skill folder (dev-toolkit/skills/one-way-door in jamditis/claude-skills-journalism) into .claude/skills/one-way-door in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jamditis/claude-skills-journalism --skill one-way-door -a codex`. Or copy the skill folder (dev-toolkit/skills/one-way-door in jamditis/claude-skills-journalism) into .agents/skills/one-way-door 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 jamditis/claude-skills-journalism --skill one-way-door -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/one-way-door, .gemini/skills/one-way-door, .github/skills/one-way-door and .opencode/skills/one-way-door in your project.
Going by SKILL.md and its folder, One Way Door needs PowerShell for the scripts in its folder and the command-line tools its instructions call (tsx, terraform and pulumi). Our summary lists: PowerShell; Docker.
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 notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
One Way Door is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5k tokens (SKILL.md is roughly 20k 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 One Way Door: Code Patterns (Aedelon/claude-code-blueprint, 120 stars), Cloud Infra Supply Chain (zhaji2333/CkSKILLS, 115 stars), Sap Btp Cloud Platform (secondsky/sap-skills, 462 stars) and Apollo Deploy Integration (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jamditis (a GitHub user) maintains it in jamditis/claude-skills-journalism, which has 416 GitHub stars. The repository holds 53 skills in this directory. The repository was last updated on October 4, 2026.
Source: jamditis/claude-skills-journalism on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.