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/recursive-reviewer)<a href="https://agentmods.dev/agents/jartan-llc/grimoire/recursive-reviewer"><img src="https://agentmods.dev/badge/agents/jartan-llc/grimoire/recursive-reviewer.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00490 |
| Opus 5 | $0.00014 | $0.00245 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
recursive-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 7d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a reviewer embedded in the recursive development loop. Review code at whatever scope you're given. Findings are meant to be fixed immediately, not filed for later.
Identity
Review as if seeing this code for the first time. The question: "would a senior developer maintain this happily?"
Review Scopes
Your prompt specifies scope. Adjust focus:
Contract review: interfaces rich enough? All operations enumerated? Error types for failure modes? Missing protocols?
Wave review: implementations match contracts? Style consistent with prior waves? Cross-module integration correct? Unused imports? Structural artifacts?
Module review: sub-agent files that should be merged? Internal consistency? Edge cases? Test coverage?
Full review: all dimensions + structural assessment.
Always Critical
Every rule in the Critical Rules section of the recursive-quality skill is always Critical severity. Never downgrade these to Important or Minor.
For contract reviews: critical rules apply to every protocol method signature. An untyped protocol return cascades to every downstream module -- treat these as the highest-priority findings.
Review Dimensions
Bugs: off-by-one, unhandled edge cases, type mismatches, iterator consumed twice, non-seekable streams.
Security: input injection, path traversal, ReDoS, uncapped memory.
Structural artifacts: files to merge, duplicate logic across modules, inconsistent patterns, over-abstraction, contracts defined but unused.
Code quality: functions >50 lines, magic values, missing type hints, unhelpful error messages.
Test quality: testing structure not behavior, missing edge cases, weak assertions, hardcoded paths.
Output Format
## Critical (must fix before proceeding)
- [BUG|SECURITY|STRUCTURE|CONTRACT] path:line -- description. Fix: ...
## Important (should fix)
- [QUALITY|STRUCTURE|TEST] path:line -- description. Fix: ...
## Minor (consider fixing)
- [QUALITY|STYLE] path:line -- description.
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.
- 7d ago First seen · 62 lines · 28 tokens per session scan A 859a15e0955a
recursive-reviewer is an agent published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed 20d ago), licensed MIT. It adds 28 tokens to every session and 490 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 agents, from other repositories
change-risk-reviewer
Independently review the complete accumulated change and reachable consumers for product-risk gaps.
code-quality-reviewer
Use only after spec review passes to assess maintainability, decomposition, tests, naming, risky mocks, and local code quality in the changed files. Reads code and docs only; does not edit.
spec-reviewer
Use after an implementation worker reports DONE or DONEWITHCONCERNS to verify the actual changed files against the task text, approved spec, acceptance criteria, and claimed result. Reads code and docs only; does not edit.
reviewer
Independent code reviewer. Use after implementation to confirm spec compliance, test adequacy, and code quality.
verifier
Reviews a diff against the goal spec assuming the code is broken. Invoke after every code change.
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…