Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mblode/agent-skills --skill pr-babysittergit clone --depth 1 https://github.com/mblode/agent-skillsWrote 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.
[](https://agentmods.dev/skills/mblode/agent-skills/pr-babysitter)<a href="https://agentmods.dev/skills/mblode/agent-skills/pr-babysitter"><img src="https://agentmods.dev/badge/skills/mblode/agent-skills/pr-babysitter.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 85 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 128 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.03833 |
| Opus 5 | $0.00036 | $0.01917 |
| Sonnet 5 | $0.00014 | $0.00767 |
| Haiku 4.5 | $0.00007 | $0.00383 |
Grade A, and why
pr-babysitter 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Babysitter
- IS: keeping one open PR moving: conflicts, CI across GitHub Actions/Buildkite/Vercel/Fly.io, inbound review comments, and merge readiness, as a background monitor or as one-shot fixes.
- IS NOT: opening or editing the PR (
pr-creator), reviewing the diff for bugs (pr-reviewer), applying a localpr-reviewerreport (tidy), or npm release PRs (autoshipwatches its own release CI; never babysit a release or Version Packages PR it drives).
Mode Selection
| Invocation | Mode |
|---|---|
| "babysit", "watch this PR", "monitor", "keep it green" | Monitor: Phase 1 once, then phases 2-5 on every event or tick |
| "fix CI", "why is CI red", "loop on CI" | One-shot Phase 3 loop |
| "resolve conflicts", "rebase onto main", "update the branch" | One-shot Phase 2 |
| "address the comments", "reply to the reviewers", "triage review comments" | One-shot Comment Triage Workflow |
| "is it ready", "what is blocking the merge" | One-shot Phase 5 report |
Standing rules, every mode:
-
Monitoring or fixing code does not by itself authorize posting replies. Post, resolve threads, or request reviews only when the user authorized that communication; otherwise prepare replies and report them.
-
Resolve
scripts/fetch-comments.shrelative to this installed SKILL.md.${CLAUDE_SKILL_DIR}below is a Claude Code adapter, not a portable environment variable. -
No setup questions. Auto-detect the PR, the CI platforms, and the defaults (poll every 2 minutes, auto-resolve noise, no auto-merge), then start. Overrides arrive inline: "poll every 5 minutes", "enable auto-merge".
-
Skip closed or merged PRs. Skip drafts (
isDraft) unless asked. -
Comment triage runs autonomously; the plan file is an audit trail, not an approval gate.
-
Speak only on transitions. A quiet poll says nothing.
Reference Files
| File | Read when |
|---|---|
references/monitoring-setup.md |
Phase 1: watch ladder detail, Monitor watch script, cron fallback, state file format, defaults |
references/merge-conflicts.md |
Phase 2: mergeStateStatus table, rebase workflow, lockfile and generated-file resolution, abort criteria |
references/ci-platforms.md |
Phase 3: gh pr checks fields and exit codes, per-platform log and retry commands, Buildkite auth chain, failure classification |
scripts/fetch-comments.sh |
Comment triage: run ${CLAUDE_SKILL_DIR}/scripts/fetch-comments.sh {N} first. One JSON document of every review, thread, and issue comment; --help prints the output shape |
references/github-api.md |
Comment triage: script output contract, manual GraphQL/REST fallback, thread accounting, anchor ladder, awaiting-reply rule, reply and resolve |
references/bot-patterns.md |
Comment triage: reviewer detection, severity mapping, merge gates, noise markers, dedup, false positives |
references/fix-plan-template.md |
Comment triage: plan file format and the legal ignore reasons |
references/verification-gate.md |
Before any commit: lint, type-check, test, knip, stray-artifact sweep |
references/git-resilience.md |
A git command hangs or fails transiently (fsmonitor wedge, stale index.lock, network blip) |
evals/evals.json |
Only when changing this skill; never during a PR task |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 2.4 KB
- references/bot-patterns.md 20 KB
- references/ci-platforms.md 7.5 KB
- references/fix-plan-template.md 5.4 KB
- references/git-resilience.md 2.0 KB
- references/github-api.md 17 KB
- references/merge-conflicts.md 4.6 KB
- references/monitoring-setup.md 9.5 KB
- references/verification-gate.md 4.4 KB
- scripts/fetch-comments.sh 16 KB runs code
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.
- 3d ago Changed · -28 lines · -69 tokens per session 0042ecce3da7
- 8d ago First seen · 220 lines · 141 tokens per session scan A 7054a019b23e
pr-babysitter is a skill published in the GitHub repository mblode/agent-skills (105 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 3,833 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
spawn-reviewers
Spawn and collect the reviewer fleet at stage20spawnreviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves GRAPHPROJECT, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified Auditor, Domain Critics, Impact…
verify-findings
Dispatch and collect the finding-verifier fleet at stage23verifyfindings (PLN-722). Reads verifymanifest.json (written by stage22bverifyprepare), spawns one falsify-oriented verifier Task per toverify[] entry with mode-specific Task scheduling (GitHub mode dispatches verifiers synchronously; local mode uses parallel…
singleton-dispatch
PLN-725 single-agent dispatch for stage11extractsignals and stage15coveragecritic. After each prepare stage writes its manifest, this skill reads the status field (cachehit / skipped / needsagent) and, only on needsagent, spawns one synchronous singleton Task that writes the by-convention pln725.json output the…
codex-review
Run Codex to review a plan file and return structured feedback with a verdict. Triggers on: debate loop Codex review rounds. Returns VERDICT:APPROVED or VERDICT:NEEDSCHANGES plus CODEXSESSION token.
critic-cache
Check if critic reviews are still valid before re-running Phase 2.5 critics. Compares plan.json + critic-gates.json content hash against stored hash from last critic run. Triggers on: entering Phase 2.5, checking critic cache, before launching critics. Returns CRITICCACHEHIT to skip critics or CRITICCACHEMISS to…
audit-harness
Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.