agentmods.dev

ijfw-cross-audit

ijfw-cross-audit is a skill for Claude Code from FerroxLabs/ijfw. It costs 67 tokens per session (1,217 once invoked), scanned A, original, MIT.

A review workflow that sends a change, file, brief, or other artifact to several independent AI reviewers for comparison.

In plain words
What is it for?
It is for cross-checking code changes, files, or written briefs with selected AI tools and comparing their findings.
Why use it?
It provides more than one perspective and can expose issues a single reviewer misses.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions Claude Code; mentions Codex.

Part of the ijfw plugin — 34 skills, 22 commands, 37 agents, 6 hooks shipped together

not rated 210repo 3d ago A scan SkillSpector: pass 67 tokens original MIT

Good fit It is for cross-checking code changes, files, or written briefs with selected AI tools and comparing their findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ferroxlabs/ijfw/ijfw-cross-audit
View source ↗ FerroxLabs/ijfw npmjs.com
Install

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.

Any agent
npx skills add FerroxLabs/ijfw --skill ijfw-cross-audit
Clone the repo
git clone --depth 1 https://github.com/FerroxLabs/ijfw

Made for: Claude Code.

Or install ijfw, the plugin that ships this one along with the rest of its 34 skills, 22 commands, 37 agents, 6 hooks.

Wrote 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.

agentmods badge for ijfw-cross-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-cross-audit/github.svg)](https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-cross-audit)
Your own site
<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-cross-audit"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-cross-audit/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.

agentmods 80×15 button for ijfw-cross-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-cross-audit"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-cross-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,217 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.01217
Opus 5 $0.00034 $0.00609
Sonnet 5 $0.00013 $0.00243
Haiku 4.5 $0.00007 $0.00122

Measured 5d ago against content hash 87d79cf86a8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ijfw-cross-audit 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 5d 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.

claude/skills/ijfw-cross-audit/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execution

  1. Detect artifact. Accept: diff, file path, brief text, or HEAD~1..HEAD. If none provided, ask once: What should I audit? (diff, file, or paste text)

  2. Detect auditors. Roster covers six independent training lineages:

    • codex (openai family) -- OpenAI CLI
    • gemini (google family) -- Gemini CLI
    • claude (anthropic family) -- Claude Code (fresh session)
    • deepseek (oss / cn lineage) -- DeepSeek API
    • qwen (oss / cn lineage) -- Qwen Code CLI
    • kimi (oss / cn lineage) -- Moonshot Kimi
    • opencode, aider, copilot (additional oss / openai-family auditors)

    Default selection: diversity strategy picks one openai-family + one google-family + caller, excluding the caller's own family. Reachability = CLI on PATH OR API key in env. The Donahoe Trident principle says: at least three lenses, three lineages.

  3. Override roster with --with. Pass --with <id>[,<id>] to pin the exact auditors fired. Self-audit is rejected (same-lineage = single source). Example: cross-audit --with codex,gemini,deepseek <target>.

  4. Dispatch in parallel. Every lens runs concurrently; the orchestrator short-circuits stragglers once minResponses productive results land. Per- provider timeouts (codex 120s, gemini 90s, default 90s) plus IJFW_AUDIT_TIMEOUT_SEC override.

  5. Reconcile. Lexical-signature clustering (issue + location):

    • CONSENSUS -- flagged by ≥2 lenses (consensus: true, consensusCount, consensusLenses)
    • CONTESTED / single-lens -- flagged by exactly 1 lens
    • PASS -- no findings Output ranks CONSENSUS findings first, then single-lens findings, each ordered by canonical severity (critical → low).

  6. Emit report using the report format rule below.

Budget controls

  • IJFW_AUDIT_BUDGET_USD (default $2.00) -- per-session aggregate cap. Post-flight accumulation; first call is always allowed, subsequent calls are rejected when accumulated + estimate > budget. Raise to continue.
  • IJFW_AUDIT_BUDGET_USD_PER_LENS -- granular cap on a single lens's spend across one convergence cycle. Useful for "spend at most $0.50 per gemini call" guardrails on long-running converge loops.
  • IJFW_AUDIT_TIMEOUT_SEC -- per-auditor budget (clamped to [1, 3600]).
  • IJFW_AUDIT_CONCURRENCY -- parallel-fire cap (default 3).

Read the full file on GitHub · 112 lines

Changes

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.

  1. 5d ago First seen · 112 lines · 67 tokens per session scan A 87d79cf86a8f

Subscribe to this mod's changes

ijfw-cross-audit is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 1,217 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 2026-09-05.

Claude CodeCode reviewai-agentsai-codingcodexcursordeveloper-tools
Related

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.

Gentleman-Programming/gentle-ai · 0 tokens

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…

Gentleman-Programming/gentle-ai · 106 tokens

issue-creation

Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.

Gentleman-Programming/gentle-ai · 30 tokens

sdd-tasks

Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.

Gentleman-Programming/gentle-ai · 25 tokens

sdd-verify

Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.

Gentleman-Programming/gentle-ai · 0 tokens

sdd-spec

Write SDD delta specs with requirements and scenarios. Trigger: orchestrator launches spec work for a change.

Gentleman-Programming/gentle-ai · 25 tokens