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.
git clone --depth 1 https://github.com/sergeyklay/.agentsWrote 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/commands/sergeyklay/.agents/resolve-review)<a href="https://agentmods.dev/commands/sergeyklay/.agents/resolve-review"><img src="https://agentmods.dev/badge/commands/sergeyklay/.agents/resolve-review/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.
<a href="https://agentmods.dev/commands/sergeyklay/.agents/resolve-review"><img src="https://agentmods.dev/badge/commands/sergeyklay/.agents/resolve-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00015 | $0.00647 |
| Opus 5 | $0.00008 | $0.00324 |
| Sonnet 5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
resolve-review 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 6d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your task is to resolve reviewer feedback on the current pull request or on comments the user provides inline.
Task
- Use the
babysit-prAgent Skill to drive every step of the resolution: ingest, classify, run the Context7 evidence audit, apply changes surgically, and produce the human-only summary. - Detect the input mode automatically:
- A GitHub PR number, URL, or the current branch's open PR → use the skill's GitHub-fetch flow.
- Pasted text or inline reviewer comments → use them as-is.
- Read the project's context files (
AGENTS.md,CLAUDE.md,CONTRIBUTING.md,README.md), and project architecture documentation so you know the coding standards, verification commands, issue tracker.
Skill Enforcement
MANDATORY: Apply the babysit-pr Agent Skill verbatim.
The skill is the single source of truth for how to resolve reviewer comments. The project's context files are the source of truth for what counts as a valid standard, verification command, and Context7-required library. Consult each at the moment the skill calls for it.
Process:
- Load the
babysit-prAgent Skill before reasoning about any comment. - Walk through each step in order - ingest, Context7 audit, classify, apply, verify, summarize. Do not reimplement, paraphrase, merge, or short-circuit any step. Every gate exists to prevent a documented failure mode.
- If the skill is unavailable in this environment, stop and report the failure. Do not improvise a replacement protocol.
- Emit the Step 6 summary directly in the chat response. The audience is the human operator, not a persistent file.
Completion
- When the input was a GitHub PR: after the summary, commit the applied changes to that PR's branch and push them. This is the expected completion rather than a separate request, and stopping to ask permission to push is itself a failure. Use the
git-commitAgent Skill, and group the changes into atomic commits along the concerns they resolve. Do not open a new PR, and do not rewrite the existing PR description unless the applied changes made it wrong. - When the input was pasted or inline feedback: leave the changes in the working tree and report them. There may be no branch to land them on.
- Report the commits alongside the summary, so the operator sees both what was decided and what landed.
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.
- 6d ago Changed · +6 lines add5365a10ad
- 9d ago First seen · 35 lines · 15 tokens per session scan A a30a0b52ef03
resolve-review is a command published in the GitHub repository sergeyklay/.agents (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 647 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
commit-and-create-mr
Commit and create MR on Gitlab.
review
Recent git commits: !git log --oneline -10.
odoo-review
Review a GitHub PR against Odoo PSDU conventions — business need, file-by-file, then full-logic; before/after fixes; terminal-only, read-only.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
review-open-prs
Command "review-open-prs" from The-Artificer-of-Ciphers-LLC/skills-from-the-artificer, covering batch pr review directive — all open prs i did not author, phase a — enumerate target prs & build the queue, phase b — per-pr directive (runs once per queued $pr), 0. context anchoring and 1. preconditions.
codex-review
Run OpenAI Codex code review on current changes or a specific branch/commit.