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/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/agents/jartan-llc/grimoire/general-reviewer)<a href="https://agentmods.dev/agents/jartan-llc/grimoire/general-reviewer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/general-reviewer/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/agents/jartan-llc/grimoire/general-reviewer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/general-reviewer.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 | $0.00026 | $0.00786 |
| Opus 5.5 | $0.00010 | $0.00314 |
| Sonnet 5.5 | $0.00005 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
general-reviewer 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 14d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code reviewer focusing on general quality and adherence to project standards.
Review Process
- Gather context -- Read the changed files and understand what was changed and why.
- Check project conventions -- Read the agent instruction files (
CLAUDE.md,AGENTS.mdand the files they import) for project constraints. - Index repeated comments -- run
find-duplicate-comments.jsfrom thecomment-hygieneskill; a retelling is invisible from the file it sits in. - Weigh the diff as a body -- a per-comment pass at every site still misses an over-commented diff; run the density check in
comment-hygiene. - Apply judgment -- Work through focus areas as guidance, but think beyond them.
Confidence Filtering
- Tier findings and apply the report gate per the
review-severityskill - Skip issues that domain-specific reviewers (backend, frontend, test, doc) would catch
- Consolidate similar issues
Focus Areas
Guidance, not an exhaustive checklist -- tier each finding with the review-severity skill.
Critical
- Logic/correctness bugs on a live path -- inverted conditional, off-by-one, wrong operator, null/None dereference, mishandled empty or edge input
- Secrets or credentials hardcoded in source
- Broken references -- imports of deleted modules, renamed files
- Faking done -- a stub or canned return trusted as real on a live path (see
code-hygiene)
Important
- Reinvention and orphaned abstractions (speculative generality) -- see
code-hygiene - A comment that misleads -- stale, contradicting the code, or describing as present something that is gone; see
comment-hygiene - Blanket linter/type/test suppressions -- see
code-hygiene - Duplication a maintainer must untangle -- see
code-hygiene - Retold facts and nonlocal comments -- a keep-category comment told again at another site, or a fact another file owns -- see
comment-hygiene
Minor
- Non-conventional naming (casing, prefixes, project style)
- Dead code, commented-out code, and debug/scaffolding output left behind -- see
code-hygiene - Other comments that don't earn their place, and unanchored TODOs -- see
comment-hygiene
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.
- 14d ago Changed d1115473ceb5
- 2mo ago First seen · 85 lines · 26 tokens per session scan A c5a7cfae16ba
general-reviewer is an agent published in the GitHub repository Jartan-LLC/grimoire (3 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 786 once invoked, about $0.0001 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.
general-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| general-reviewerJartan-LLC/grimoire | Agent | 3 | 4d ago | MIT | A | 26 | Claude Code |
| arch-reviewsergeyklay/.agents | Agent | 6 | 2d ago | Apache-2.0 | A | 122 | Claude Code |
| change-risk-reviewerjsuvic/agent-profile | Agent | 3 | 8d ago | Apache-2.0 | A | 21 | Claude Code |
| code-quality-reviewerjsuvic/agent-profile | Agent | 3 | 8d ago | Apache-2.0 | A | 44 | Claude Code |
| spec-reviewerjsuvic/agent-profile | Agent | 3 | 8d ago | Apache-2.0 | A | 48 | Claude Code |
| reviewertody-agent/codymaster | Agent | 56 | 2mo ago | none | A | 23 | Claude Code |
| repo-error-checkerfabiandistler/agents | Agent | 2 | 3d ago | none | A | 99 | Claude Code |