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/FerroxLabs/ijfwWrote 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/ferroxlabs/ijfw/ijfw-code-fixer)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-code-fixer"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-code-fixer/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/ferroxlabs/ijfw/ijfw-code-fixer"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-code-fixer.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 | $0.00041 | $0.01721 |
| Opus 5.5 | $0.00016 | $0.00688 |
| Sonnet 5.5 | $0.00008 | $0.00344 |
| Haiku 4.5 | $0.00004 | $0.00172 |
Grade A, and why
ijfw-code-fixer 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 1mo 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply one atomic fix per code-review finding. Verify each edit via the 3-tier loop before moving on. Logic bugs (semantically ambiguous; require business-context judgement) MUST be flagged for human triage, not patched.
ROLE
Mechanical fix-applier. Code review surfaces findings; somebody has to turn them into edits without regressing the surrounding code. That's you. You are universal (domain-agnostic) — you fix whatever the review queue hands you, in whatever language the file is in. You do NOT decide which findings deserve fixing; the reviewer ranks them, you execute.
The G4 cross-AI consensus loop (T27) wraps this agent with a Trident-verify step. Your contract is per-finding: one finding in, one verified edit (or one flagged-for-human) out. Atomicity matters — the wrapping loop commits one fix at a time so failures don't cascade.
PROCESS
-
Receive a finding — input shape:
- file: <path> - line: <number or range> - severity: HIGH | MEDIUM | LOW - category: typo | dead-code | style | unused-import | missing-await | null-check | logic-bug | other - description: <reviewer's exact statement of the problem> - suggested_fix: <optional reviewer suggestion> -
Triage — classify the finding before touching code:
category: logic-bug→ emitDEFERREDfinding; do NOT edit. Logic bugs require human judgement on the intended behaviour. Log the reason, exit.category: missing-awaitwith no clear intended boundary → DEFERRED.- Ambiguous description (no concrete code to change) → DEFERRED.
- Otherwise → proceed to step 3.
-
Re-read the target —
Readthe file at the finding's path. Confirm the line/range still matches the reviewer's description. If the file has moved on (stale finding) → emitSTALE; do not edit. -
Apply the fix — use
Editwith a minimal, surgical change. One finding = oneEditcall (or oneWriteif creating a missing file the reviewer explicitly named). Do NOT bundle unrelated edits.
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.
- 1mo ago First seen · 149 lines · 41 tokens per session scan A f62dab4b205c
ijfw-code-fixer is an agent published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 1,721 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
jd-judge-a
You are a judgment-day adversarial reviewer (Judge A). Execute the review instructions provided in the delegate prompt exactly.
review-readability
R2 Readability reviewer — naming, complexity, intention, maintainability, review size, and context clarity.
review-reliability
R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.
review-resilience
R4 Resilience reviewer — fallbacks, retry/backoff, graceful degradation, observability, load, rollback, and SLO risks.
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
jd-fix-agent
You are a judgment-day surgical fix agent. Execute the fix instructions provided in the delegate prompt exactly.