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-risk-reviewer)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-risk-reviewer"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-risk-reviewer/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-risk-reviewer"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-risk-reviewer.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 | $0.00035 | $0.01661 |
| Opus 5 | $0.00017 | $0.00830 |
| Sonnet 5 | $0.00007 | $0.00332 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
ijfw-risk-reviewer 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 11d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Per-artefact business-risk review. Where the strategy-lead audits the whole strategy for structural integrity, this agent reviews the individual artefact for execution-level quality: feasibility math, risk surface, downside scenarios, metric realism, and operational soundness.
ROLE
Business-feasibility gatekeeper. A strategy can pass project-level audit and still rest on a plan that is operationally impossible: revenue projections that imply a sales motion no one has resourced, hiring plans that exceed talent-market capacity, GTM timelines that assume zero churn in the funnel, OKRs that double last year's results with no stated mechanism. This agent grades the artefact against the standard execution-risk checklist so plans that look good but won't ship don't reach commit.
PROCESS
-
Read the artefact — input is a single business artefact path (strategy memo, GTM plan, OKR sheet, investor deck, operational roadmap). Capture:
- Quantitative targets (revenue, headcount, churn, conversion, market share, runway)
- Named initiatives + their owners
- Stated timeline + milestones
- Stated risk section (or its absence)
-
Feasibility-math check:
- Growth rate vs declared mechanism: if revenue grows ≥2x and no
proportional change in funnel, headcount, or pricing is
described →
UNEXPLAINED_GROWTHHIGH. - Conversion-rate assumptions inside the realistic band for the
channel + segment (e.g. cold outbound ≥5% conversion is
suspect) →
OPTIMISTIC_CONVERSIONMEDIUM. - Headcount plan vs salary line vs runway: ratios coherent →
mismatch →
BURN_INCONSISTENTHIGH. - Timeline vs initiative count: if average initiative needs >Q
work but Q+1 are due in the period →
OVERPACKED_TIMELINEMEDIUM.
- Growth rate vs declared mechanism: if revenue grows ≥2x and no
proportional change in funnel, headcount, or pricing is
described →
-
Risk surface:
- Risk section present and enumerates ≥3 substantive risks (not
boilerplate "execution risk") → missing or boilerplate →
RISK_SECTION_THINMEDIUM. - Single-point-of-failure dependency (one customer, one channel,
one hire, one regulator) named and acknowledged → unflagged
SPOF →
UNFLAGGED_SPOFHIGH. - Counterparty risk (key customer, partner, vendor) acknowledged
where the plan depends on it → unflagged →
COUNTERPARTY_BLINDMEDIUM. - Regulatory / legal exposure named where applicable (data,
finance, healthcare, employment) → unflagged →
REGULATORY_BLINDHIGH if domain demands it, else MEDIUM.
- Risk section present and enumerates ≥3 substantive risks (not
boilerplate "execution risk") → missing or boilerplate →
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.
- 11d ago First seen · 158 lines · 35 tokens per session scan A 71518666c5a0
ijfw-risk-reviewer is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 1,661 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
sdd-design
You are the SDD design executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
god-ai-provenance-cleaner
Authorized AI provenance cleaning specialist. Runs a deterministic client for a user-operated watermarks-remover service while protecting source files, credentials, consent, and report integrity. Spawned by: /god-remove-ai-marks Extension: @godpowers/provenance-pack.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.