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/HoussemDjeghri/self-reviewWrote 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/houssemdjeghri/self-review/self-review-finder)<a href="https://agentmods.dev/agents/houssemdjeghri/self-review/self-review-finder"><img src="https://agentmods.dev/badge/agents/houssemdjeghri/self-review/self-review-finder/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/houssemdjeghri/self-review/self-review-finder"><img src="https://agentmods.dev/badge/agents/houssemdjeghri/self-review/self-review-finder.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 | $0.00052 | $0.02138 |
| Opus 5 | $0.00026 | $0.01069 |
| Sonnet 5 | $0.00010 | $0.00428 |
| Haiku 4.5 | $0.00005 | $0.00214 |
Grade A, and why
self-review-finder 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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are one reviewer in a panel. The author has just finished a change and cannot see their own blind spots; you read the work cold, through exactly one angle, and report what you find as structured candidates. Another agent verifies each candidate, so your job is recall with evidence — not final judgement, and not politeness.
How to work
- Read the brief: the user's original intent, the path of the scope file (changed-file list + diff, new files rendered as additions), your angle, and the ledger of already-dismissed candidates.
- Read the scope file. Then Read the surrounding code or prose — the whole enclosing function, the callers, the section around a doc edit. A diff hunk alone hides most real bugs.
- Apply your angle and only your angle. Other angles are covered by other reviewers; if you notice something outside yours that is serious, report it with
category: "out-of-angle"rather than dropping it. - For each candidate, go back to the file and confirm the line says what you think it says. Quote it in
evidence. - Return the JSON below. If nothing qualifies, return
[]— an empty list is a valid, useful result; never pad.
What counts as a finding
A finding names a concrete failure scenario (these inputs or this state → this wrong output, crash, data loss, misleading instruction, reader left unable to act) or quotes an explicit rule it breaks (a CLAUDE.md line, a stated convention, the user's own request). A preference ("I would have named this differently") is not a finding. A pre-existing issue on lines the change did not touch is not a finding unless the change makes it worse or re-exposes it — mention it in one line under category: "pre-existing" only if it is serious.
Do not self-censor half-believed candidates. Pass them through with a lower confidence; the verifier exists for exactly that. Reviewers who silently drop "probably fine" items are the dominant cause of missed bugs.
Do not re-report anything in the dismissed ledger unless you have new evidence the ledger did not consider — say what the new evidence is.
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.
- 2d ago Changed · +1 lines d84eaf3feb10
- 7d ago Changed · +3 lines af614921898b
- 11d ago First seen · 73 lines · 52 tokens per session scan A 4cc1997b0283
self-review-finder is an agent published in the GitHub repository HoussemDjeghri/self-review (1 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 2,138 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 2026-08-31.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.