claude-code-config: Skill for Claude Code

.claude/skills/babysit-pr-stop/SKILL.md

babysit-pr-stop is a skill for Claude Code from auerbachb/claude-code-config. It costs 52 tokens per session (1,662 once invoked), scanned A, original, MIT.

A command that cleanly stops a running pull-request watcher. It records the stop request, stops the watcher's monitoring task, and confirms the result.

In plain words
What is it for?
Use it to stop monitoring a specific pull request.
Why use it?
It lets you cancel monitoring without merging or changing the pull request itself. Repeating it when no watcher exists is safe.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

This is auerbachb/claude-code-config's own configuration. It tells Claude Code how to work on claude-code-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to auerbachb/claude-code-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/auerbachb/claude-code-config/main/.claude/skills/babysit-pr-stop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for babysit-pr-stop

README.md
[![agentmods](https://agentmods.dev/badge/skills/auerbachb/claude-code-config/babysit-pr-stop/github.svg)](https://agentmods.dev/skills/auerbachb/claude-code-config/babysit-pr-stop)
Your own site
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/babysit-pr-stop"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/babysit-pr-stop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for babysit-pr-stop

Your own site · 80×15
<a href="https://agentmods.dev/skills/auerbachb/claude-code-config/babysit-pr-stop"><img src="https://agentmods.dev/badge/skills/auerbachb/claude-code-config/babysit-pr-stop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,662 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01662
Opus 5.5 $0.00021 $0.00665
Sonnet 5.5 $0.00010 $0.00332
Haiku 4.5 $0.00005 $0.00166

Measured 2mo ago against content hash aad8ea5bc328, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

babysit-pr-stop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/babysit-pr-stop/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stop the /babysit-pr watcher for one PR. This is the clean-cancel companion to /babysit-pr — it does not merge, fix, or touch the PR itself; it only tears down the watcher Monitor and its state.

Stopping is exact and idempotent: it records the stop request, stops the recorded Monitor task with TaskStop, and leaves the watcher's T0 short-circuit armed for any tick that was already emitted. Running it on a PR with no active watcher is a safe no-op.

Resolve the state helper

Same three-candidate lookup as /babysit-pr (fixpr/SKILL.md pattern):

resolve_script() {
  local name="$1" candidate
  for candidate in \
    "$HOME/.claude/skills-worktree/.claude/scripts/$name" \
    "$HOME/.claude/scripts/$name" \
    ".claude/scripts/$name"; do
    if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
  done
  return 1
}
SESSION_STATE_SH=$(resolve_script session-state.sh) || { echo "ERROR: session-state.sh not found" >&2; exit 1; }

Steps

1. Parse the PR number

The first bare integer in $ARGUMENTS is <PR>. If none is given, stop: "Usage: /babysit-pr-stop ".

2. Check for an active watcher

Distinguish "no watcher" from "the state helper failed" — do not collapse every error into a clean no-op (that would silently skip a real stop request):

ACTIVE=$("$SESSION_STATE_SH" --get ".prs[\"$PR\"].babysit.active"); GET_RC=$?
case "$GET_RC" in
  0) ;;                                   # value read OK (may be true/false/null)
  3) echo "No babysit state on file — nothing to stop."; exit 0 ;;  # state file missing
  *) echo "ERROR: session-state.sh --get failed (exit $GET_RC) — not assuming inactive; investigate before retrying." >&2; exit "$GET_RC" ;;
esac
if [[ "$ACTIVE" != "true" ]]; then       # only a genuine null/false means inactive
  echo "No active babysit watcher for PR #$PR — nothing to stop."
  exit 0
fi

Exit 3 (state file absent) is the legitimate "nothing to watch" case. Any other non-zero exit is a real helper/parse failure — surface it and stop rather than masking it as inactive.

Read the full file on GitHub · 123 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 123 lines · 52 tokens per session scan A aad8ea5bc328

Subscribe to this mod's changes

babysit-pr-stop is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,662 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

robin

Use whenever an agent creates, updates, reviews, or completes a GitHub pull request. Detect whether Robin is installed in the repository; when it is, automatically drive the PR through a bounded review, verified-fix, reply, thread-resolution, re-review, authorized-merge, and cleanup loop without requiring the user to…

antongulin/robin · 92 tokens

revert

Git-aware revert that understands Draft tracks, phases, and tasks. Safely undo work at task, phase, or track level. Use when the user asks to 'revert this track', 'undo a phase', 'revert task X', or says 'roll back the last task', 'undo this work'.

drafthq/draft · 66 tokens

upload

Pre-upload gate for track handoff. Verifies review status, HLD approvals, deploy checklist, and validator chain before git upload or PR submission.

drafthq/draft · 32 tokens

bump-version

Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the README badge), then validate. Use when cutting a release or when npm run validate reports a version mismatch.

hyhmrright/logic-lens · 52 tokens

kodus-business-rules-validation

Use when the user wants Kodus to validate local diff changes against task requirements, acceptance criteria, or business rules via kodus pr business-validation, especially for implementation-vs-task or merge readiness checks.

kodustech/kodus-ai · 48 tokens

Cross-File Leakage リファクタ後の caller 側残骸検出

A code review check for structural changes such as renamed functions, changed arguments, moved files, or split modules. It searches the rest of the project for callers that still use the old structure.

s977043/river-review · 79 tokens