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 Jartan-LLC/grimoire --skill address-reviewgit clone --depth 1 https://github.com/Jartan-LLC/grimoireWrote 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/jartan-llc/grimoire/address-review)<a href="https://agentmods.dev/skills/jartan-llc/grimoire/address-review"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/address-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/skills/jartan-llc/grimoire/address-review"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/address-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 | $0.00014 | $0.00485 |
| Opus 5 | $0.00007 | $0.00243 |
| Sonnet 5 | $0.00003 | $0.00097 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
address-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 12d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address Review
Work through code review findings on a pull request, investigating each one and applying fixes where warranted.
Always pause for the user's decision on each finding -- even in auto mode, even if the reviewer or your own assessment recommends skipping. Auto mode grants tool access, not decision authority; the user decides what to fix, skip, or adjust.
Process
1. Load Review
Determine the PR number from the user's request. Fetch the review comments:
gh pr view <pr-number> --comments
There may be multiple review comments in the history -- use only the most recent one. Parse its findings into a numbered list grouped by severity (Critical > Important > Minor).
2. Check Out Branch
Ensure the PR's branch is checked out locally so fixes can be applied.
3. Walk Through Findings
Work through each finding sequentially. For each one:
- Investigate -- Read the relevant code. Understand whether the finding is a real problem, a theoretical concern, or a false positive. Check how the rest of the codebase handles the same pattern.
- Assess -- Present your assessment to the user: is it a real issue, valid but not applicable here, or wrong? Propose a specific fix or recommend skipping, with reasoning.
- Act on user decision -- Apply the fix, skip it, or adjust based on the user's response.
Do NOT blindly apply every suggestion. Investigate first -- the reviewer may have missed context, flagged a pattern that's intentional, or suggested a fix that creates inconsistency with the rest of the codebase.
When the user agrees to skip a finding, post a brief PR comment explaining why it was declined:
gh pr comment <pr-number> --body "**Re: <finding title>** -- <concise reason for skipping>"
4. Commit
The user may ask to commit at any point during the review -- commit what's been done so far and continue with the remaining findings. Use the format:
fix(<scope>): address code review findings
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.
- 12d ago First seen · 54 lines · 14 tokens per session scan A 63f47a3abd67
address-review is a skill published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 485 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 skills, from other repositories
review-arch
Conduct a principal-level architecture review of a system, specification, diagram, or set of design decisions. Use when asked to review an architecture, evaluate a design, assess coupling/cohesion, check for anti-patterns, audit system boundaries, or produce an Architecture Review Board (ARB) style verdict. Also use…
review-impl
Review implementation changes for a given task against architectural standards. Use when reviewing a PR, evaluating recently committed code, assessing whether implementation changes are correct and architecturally sound, or when asked to 'review my changes', 'check this implementation', 'review what I built', 'is this…
survey
After building a feature (or evaluating a plan), verify it matches what was planned, respects the project's declared architecture and standards, and is production-ready. Reports issues clearly and routes broken behavior to dredge or contested judgment calls to watershed.
watershed
Get a wider, multi-angle critique of code, a plan, or an idea through five distinct critical perspectives, followed by a sixth consolidation pass. Use when a decision is contested, high-stakes, or one careful survey is not enough.
design-parity-review
Prove a Compose UI pull request matches its intended design by diffing the rendered code (candidate) against a Figma / Stitch / Claude Design reference and posting a parity verdict. Use when asked to check a PR against a design, wire up a design-parity bot, set up the committed reference cache so runs make zero Figma…
compose-preview-review
Review pull requests that change Compose UI by rendering @Preview composables on base and head and diffing them. Use when reviewing a UI PR locally or from a CI agent session (@claude mention), authoring an agent-opened PR that touches UI, or triaging flaky or unstable previews (time/random/animation). Pairs with the…