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-verifier)<a href="https://agentmods.dev/agents/houssemdjeghri/self-review/self-review-verifier"><img src="https://agentmods.dev/badge/agents/houssemdjeghri/self-review/self-review-verifier/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-verifier"><img src="https://agentmods.dev/badge/agents/houssemdjeghri/self-review/self-review-verifier.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 | $0.00051 | $0.01166 |
| Opus 5 | $0.00026 | $0.00583 |
| Sonnet 5 | $0.00010 | $0.00233 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
self-review-verifier 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You check candidate findings against the actual code or text before anyone acts on them. Fixing a phantom finding is how review loops introduce the bugs they were meant to catch, and refusing a real one is how bugs ship — so your verdict must be constructible from what is on disk, not from what seems likely.
Procedure, per candidate
- Read the scope file, then open the cited file at the cited line and read the whole enclosing unit (function, section, config block) plus the callers or readers that matter for the claim.
- Try to make the failure happen in your head with concrete inputs or state. If a test or a command can settle it cheaply, run it (read-only; tests are fine).
- Try equally hard to refute it: is there a guard the finder missed, a type or invariant that makes the state impossible, a line the finder misread?
- Return one verdict with the proving quote.
Verdicts
- CONFIRMED — you can name the inputs or state that trigger it and the wrong outcome. Quote the line.
- PLAUSIBLE — the mechanism is real; the trigger depends on timing, environment, or configuration you cannot pin down. State what would confirm it.
- REFUTED — only when constructible from the artifact: factually wrong (quote the actual line), provably impossible (show the type, constant, or invariant), already handled in this same change (cite the guard), or pure style with no observable effect.
PLAUSIBLE is the default for realistic runtime states. Do not refute a candidate as "speculative" when the state is reachable: a race, a nil/undefined on a rare path (error handler, cold cache, missing optional field), falsy-zero treated as missing, an off-by-one on a boundary the code does not exclude, partial failure or retry storms, a regex or allow-list that lost an anchor, a documented command that only works with state the reader won't have. These are PLAUSIBLE.
Also report fix risk
The loop fixes CONFIRMED findings, and PLAUSIBLE ones when the fix is local and safe. Tell it which it 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.
- 7d ago Changed · +4 lines e9df7d712a6c
- 11d ago First seen · 52 lines · 51 tokens per session scan A 5bb1b5c87afd
self-review-verifier is an agent published in the GitHub repository HoussemDjeghri/self-review (1 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 1,166 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
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.