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-critiquegit 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-critique)<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-critique"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-critique/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-critique"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-critique.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 | $0.00055 | $0.01133 |
| Opus 5.5 | $0.00022 | $0.00453 |
| Sonnet 5.5 | $0.00011 | $0.00227 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
ijfw-critique 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before you agree, disagree. Before you advise, stress-test.
When the user asks you to critique, review a decision, or give a second opinion -- or when the intent router flags critique intent -- follow this pattern rather than answering from the same frame they asked from.
Four-step critique
-
Steelman first. In one sentence, state the strongest version of the current plan / decision / design. Not to flatter -- to make sure you're critiquing the real thing, not a caricature.
-
Surface the assumptions. Name 2-3 assumptions the plan rests on. These are the load-bearing beliefs that, if wrong, collapse the argument. Be specific: "assumes traffic stays under 10k qps", not "assumes scale".
-
Three concrete counter-arguments. Each should be:
- Non-obvious (if the user already considered it, skip)
- Bounded (state when it applies; rarely are counter-arguments universal)
- Actionable (each comes with a "watch for X" or "test by Y")
Prefer counter-arguments that come from different angles: operational, social/organizational, economic, correctness. One bug-class concern is worth less than one operational + one social + one correctness concern.
-
State your verdict briefly. After laying out the counters, give a 1-line recommendation: proceed / proceed with X mitigation / stop and rework because Y. Own the verdict -- don't just hedge.
Refactor reframe (single-line trigger)
When the user is mid-refactor and a fix feels hacky, or you catch yourself patching around a smell rather than removing it, run this prompt out loud:
Knowing everything I know now, what would the elegant solution look like?
Answer it briefly (3-5 lines). If the elegant version costs less than the hack you're about to ship, replace the hack. If it costs more than 2x, log the elegant version as a follow-up and proceed with the pragmatic fix -- but only after you've named the debt explicitly.
Skip this for trivial or obvious fixes; the point is to break frame on non-trivial decisions, not to over-engineer.
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 · 104 lines · 55 tokens per session scan A 73b395776ee0
ijfw-critique is a skill published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 1,133 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 2026-09-05.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
subagent-driven-development
A development workflow in which a fresh coding agent implements each independent task, another review checks that task, and a final review examines the complete set of changes.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.