ijfw-dep-audit

ijfw-dep-audit is an agent for Claude Code from FerroxLabs/ijfw. It costs 28 tokens per session (1,157 once invoked), scanned A, original, MIT.

A pre-release checker that compares package versions, dependency versions, publishing settings, lockfiles, and documentation across a repository. A lockfile records the exact dependency versions selected for a project.

In plain words
What is it for?
Use it before a release to inspect every package.json and lockfile, compare package versions, check publish settings and Node.js requirements, and verify documented versions.
Why use it?
It exposes mismatches and configuration drift that can cause publishing or installation failures.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

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

Good fit Use it before a release to inspect every package.json and lockfile, compare package versions, check publish settings and Node.js requirements, and verify documented versions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ferroxlabs/ijfw/ijfw-dep-audit
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.

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-dep-audit

README.md
[![agentmods](https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-dep-audit.svg)](https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-dep-audit)
Your own site
<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-dep-audit"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-dep-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,157 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.
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 $0.00028 $0.01157
Opus 5 $0.00014 $0.00579
Sonnet 5 $0.00006 $0.00231
Haiku 4.5 $0.00003 $0.00116

Measured 9d ago against content hash d30224cebced, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ijfw-dep-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 9d 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/agents/ijfw-dep-audit.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Walk every package.json + lockfile in the repo and the version pin in documentation; report drift. v1.4.4's r13 fix-wave hit EUSAGE provenance: null because publishConfig.provenance: true was added without considering the local-publish flow. This agent makes that class of drift visible before ship.

ROLE

Dependency hygiene gatekeeper. Pre-ship in v1.4.4 we had to revert publishConfig.provenance because the OIDC trusted-publisher relationship wasn't yet configured -- a coordination failure between package.json and infrastructure state. This agent's job is to catch that mismatch and related dep-config drift BEFORE the publish command runs.

PROCESS

  1. Enumerate package.jsons -- Glob for **/package.json (ignore node_modules/). Read each. Extract:

    • version
    • publishConfig
    • dependencies + devDependencies (top-level only; recursion via lockfile)
    • engines.node
  2. Cross-check versions across packages:

    • installer/package.json and mcp-server/package.json versions must match each other (IJFW invariant).
    • claude/plugin.json (if exists) version must match.
    • Documentation version mentions (CHANGELOG.md top entry, README.md badges) must match.
    • Finding VERSION_DRIFT when any pair disagrees.
  3. Cross-check publishConfig:

    • Both installer/ and mcp-server/ must have the SAME publishConfig keys (provenance, access, registry). Asymmetric config = drift.
    • Finding PUBLISH_CONFIG_DRIFT for any key present in one but not the other.
  4. Lockfile vs package.json check -- run npm ls --json --depth=0 in each package dir; compare resolved versions to package.json constraints.

    • Mismatch -> LOCKFILE_DRIFT finding.
    • Skip if node_modules doesn't exist (NEEDS_INSTALL note instead).
  5. Engine constraint check -- confirm engines.node matches the version pinned in CI (.gitlab-ci.yml image: node:24 etc).

    • Mismatch -> ENGINE_DRIFT finding.

Read the full file on GitHub · 124 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. 9d ago First seen · 124 lines · 28 tokens per session scan A d30224cebced

Subscribe to this mod's changes

ijfw-dep-audit is an agent published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,157 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

god-oss-release-strategist

Open source library release strategist. Knows package conventions, version signaling, READMEs that get used. Refuses ghost projects (READMEs without examples that work). Spawned by: /god-oss-release Extension: @godpowers/launch-pack.

hannsxpeter/godpowers · 64 tokens

release-auditor

Internal dynos-work agent. Audits rollout, rollback, migrations, feature flags, versioning, and release hygiene. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from conversation, or outside a dynos-work task.

dynos-fit/dynos-work · 66 tokens

release-executor

Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.

dynos-fit/dynos-work · 67 tokens

deployer

Deployment specialist for release readiness, merge strategy, and rollout safety checks.

fall-out-bug/sdp · 17 tokens

release-validator

Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.

rlajous/claude-code-commands · 25 tokens

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.

zxpmail/ReqForge · 0 tokens