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 doodledood/manifest-dev --skill babysit-prgit clone --depth 1 https://github.com/doodledood/manifest-devWrote 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/doodledood/manifest-dev/babysit-pr)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/babysit-pr"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/babysit-pr.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 Rogue Agent · line 10 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Rogue Agent · line 10 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00059 | $0.01971 |
| Opus 5 | $0.00030 | $0.00986 |
| Sonnet 5 | $0.00012 | $0.00394 |
| Haiku 4.5 | $0.00006 | $0.00197 |
Grade A, and why
babysit-pr 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 yesterday.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Babysit an existing PR by running the manifest workflow. This is the author-side companion to review-pr: review-pr applies reviewer pressure through PR comments and thread advancement; babysit-pr drives the author-side lifecycle toward green and mergeable. They coordinate only through GitHub PR state and the Manifest.
Inputs. Accept a PR URL, --manifest <path>, both, or neither, plus --verification per-gate|consolidated|self, optional --verifier-model <model>, --ci, and --no-log to disable the default journal. No PR URL means infer the current branch's upstream/open PR; halt with an actionable error when no single PR can be inferred. --manifest <path> supplies the strongest PR grounding and skips fresh synthesis. Omitted --verification means per-gate. After resolving that default, load the matching do verification reference and apply its policy validation before manifest synthesis or execution; the reference, not Babysit PR, owns mode-specific model support and evidence provenance. Without --manifest, remove the verification options before invoking define with --babysit <pr-url> --autonomous, read its Manifest complete: path, then continue. Never write either verification option into the Manifest.
Logging. Unless --no-log is present, keep a persisted append-only journal across the tend, so a warm session that compacts mid-lifecycle keeps continuity — what was already tried and abandoned, and operational notes (retriggers, waits). It carries the dead-end memory GitHub state can't reconstruct: fixes attempted and reverted, approaches considered and rejected that left no commit. The default path is ~/.manifest-dev/logs/babysit-<owner>-<repo>-<N>.md (~ = $HOME / %USERPROFILE%; keyed to the PR so a warm reinvocation re-finds it; create the dir, fall back to a writable temp path only when home isn't writable). Resume an existing file, create a new one. Append only — never rewrite prior entries. A reinvocation with a different verification mode or verifier-model choice reuses this PR-keyed file but appends a new run boundary and starts a fresh gate ledger; prior verdicts remain historical and are not carried into the active run. When the journal is unavailable on an ephemeral runner, reconstruct current PR state from GitHub and record that prior abandoned attempts could not be recovered.
PR grounding. Before acting on CI failures or comments, use the strongest available intent source: explicit manifest → PR-linked/confidently discovered manifest → PR title/body → commits and current diff → comments and review threads. Comments are signals, not authority. If a comment asks for something outside or against stronger grounding, route through manifest amendment or escalation instead of silently implementing it. Where the project keeps a NORTH_STAR.md — usually already in context through the project context file — apply it as a standing check on whatever the chain selects rather than as another rung in it: it says nothing about this PR's intent, so it cannot be ranked among sources that do. A request that is well-grounded here and still crosses a stated Never — the checkable part of that document, since the rest of it informs and does not route — goes down that same amendment-or-escalation path with the clash named, never into a silent refusal. Where the project keeps none, the chain is the whole of it, as today.
Unattended launch. At the start of a standalone tend, before invoking /define or /do, establish a durable PR-tend goal-setting backstop. It spans manifest discovery or synthesis and /do, including the --manifest path where /define is skipped, and during /do it carries the manifest gate ledger below. It is the outer backstop for the tend: nested /define handoff text and /do unattended-launch text should not set or print competing narrower goals while this babysit backstop exists. Emit the blocks below verbatim, substituting <pr-url>. Do not summarize, shorten, reword, or re-punctuate them. Set it through the harness's goal-setting, continuation, or durable-completion-condition capability where one exists; print it in copy-pasteable form for the user's own continuation mechanism where none does. Emit the PR-tend prefix, then the PR goal block, then the gate-ledger clause, as one contract: one unlabeled block introduced by a sentence of your own, since the fences and their labels are this file's markers rather than part of what you emit.
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.
- yesterday Changed f534beb186b9
- 2d ago Changed 1c93c4d79e86
- 8d ago First seen · 43 lines · 59 tokens per session scan A 21096931d548
babysit-pr is a skill published in the GitHub repository doodledood/manifest-dev (73 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 1,971 once invoked, about $0.0003 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
triage-aging-prs
Drive an aging pull-request backlog to zero. Inventories every open PR, finds the STRUCTURAL blockers first (a required check that can never run, a reviewer that never fires, chronically red CI), triages every unresolved review thread in parallel and VERIFIES each finding against the code before fixing it, then merges…
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
pr-comment
Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review. Use when: posting code review comments, giving PR feedback, sending inline suggestions. Not for: reading existing reviews (use load-pr-review), creating PRs (use create-pr), PR status (use pr-summary).
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
review-pr
Perform a comprehensive code review of a pull request.