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.
npx skills add FerroxLabs/ijfw --skill ijfw-receiving-reviewgit 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/skills/ferroxlabs/ijfw/ijfw-receiving-review)<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-receiving-review"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-receiving-review/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/skills/ferroxlabs/ijfw/ijfw-receiving-review"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-receiving-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.01842 |
| Opus 5 | $0.00037 | $0.00921 |
| Sonnet 5 | $0.00015 | $0.00368 |
| Haiku 4.5 | $0.00007 | $0.00184 |
Grade A, and why
ijfw-receiving-review 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IJFW Receiving Review -- technical rigor over performance
Paired with ijfw-review (reviewer side). This is the implementer side: how to react to findings from ijfw-review, ijfw-cross-audit, a human PR reviewer, a book editor, a design critic, or any other source -- without two failure modes.
Failure mode A: blind agreement. "You're absolutely right!" then implement. The finding was never verified. Half the time the reviewer was wrong, the cited line moved, or the suggested fix breaks an invariant they did not know about. You now own a regression.
Failure mode B: performative pushback. "I disagree, this is fine." No technical specifics, no citation, no evidence. Reviewer pushes back harder. You either cave (back to A) or dig in (the regression ships anyway).
The rule: every finding gets ONE of three legitimate replies, and each reply has an evidence bar.
1. Three legitimate replies to a finding
Pick ONE per finding. Never "I'll think about it" -- that is silent deferral and rots the review thread.
- Agree-and-fix -- reproduce the finding, accept it, change the code, link the commit.
- Disagree-with-reason -- cite the file, the line, the contract, the test, or the invariant that makes the finding wrong. No vibes.
- Need-more-info -- ask ONE specific question. Not "can you explain?" Instead: "you flagged L42 as a null deref -- is the concern the early-return path on L38 or the catch block on L51?"
If you cannot pick one within 60 seconds of reading the finding, you have not understood it yet. Re-read it twice before replying.
2. Before agreeing -- verify the finding is real
Reproduce it. Open the cited file at the cited line. Run the failing command, the failing test, the failing query. If the bug does not reproduce, that is a Disagree-with-reason -- and a memory entry about the reviewer's hit rate.
A finding you cannot reproduce is a finding you cannot fix. "Agreeing" without reproduction means you will guess at a fix, the guess will be wrong, and the next reviewer round will flag it again.
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 · 123 lines · 75 tokens per session scan A c5151980cafd
ijfw-receiving-review is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 5d ago), licensed MIT. It adds 75 tokens to every session and 1,842 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-spec
Write SDD delta specs with requirements and scenarios. Trigger: orchestrator launches spec work for a change.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
sdd-verify
Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.