agentmods.dev

ijfw CLAUDE.md

ijfw CLAUDE.md is an instructions file for coding agents from FerroxLabs/ijfw. It costs 1,924 tokens per session, scanned A, original, MIT.

Project instructions for IJFW, a Node.js and Bash plugin system that packages configuration for multiple AI coding agents.

In plain words
What is it for?
Use them when working on agent packages, configuration files, the memory server, scripts, dashboards, tests, or release checks.
Why use it?
They describe the project structure, platform-specific packages, testing rules, and release safeguards, helping an agent make changes without breaking supported integrations.

Instructions file

not rated 210 11d ago A scan 1,924 tokens original MIT
View the source file FerroxLabs/ijfw
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.

agentmods
npx agentmods add instructions/ferroxlabs/ijfw/claude-md
Clone the repo
git clone --depth 1 https://github.com/FerroxLabs/ijfw

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ferroxlabs/ijfw/claude-md.svg)](https://agentmods.dev/instructions/ferroxlabs/ijfw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ferroxlabs/ijfw/claude-md"><img src="https://agentmods.dev/badge/instructions/ferroxlabs/ijfw/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,924 This file is loaded in full into every session.
When invoked 1,924 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01924 $0.01924
Opus 5 $0.00962 $0.00962
Sonnet 5 $0.00385 $0.00385
Haiku 4.5 $0.00192 $0.00192

Measured 5d ago against content hash f92479832ff3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ijfw CLAUDE.md 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.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IJFW -- Project Context

Stack: Node.js / Bash / Markdown Architecture: Plugin system -- ships platform-native packages for 15 AI coding agents Author: Sean Donahoe

Structure

  • claude/ -- Claude Code plugin (full featured: skills, hooks, agents, commands)
  • codex/ -- Codex CLI config + instructions
  • gemini/ -- Gemini CLI MCP config + GEMINI.md
  • cursor/ -- Cursor MCP config + .cursorrules
  • windsurf/ -- Windsurf MCP config + .windsurfrules
  • copilot/ -- Copilot MCP config + instructions
  • hermes/ -- Hermes CLI HERMES.md + MCP registration for ~/.hermes/config.yaml
  • wayland/ -- Wayland CLI WAYLAND.md + MCP registration for ~/.wayland/config.yaml
  • aider/ -- Aider rules-only tier (~/.aider.conf.yml + ~/CONVENTIONS.md)
  • universal/ -- 20-line paste-anywhere rules file
  • mcp-server/ -- Cross-platform MCP memory server (Node.js, zero deps)
  • scripts/e2e-smoke.sh -- end-to-end test harness (30+ gates across 2 modes); manual operator gate before publish (not CI-runnable: Mode 1 hashes the operator's real home-dir configs). CI enforces preflight + check-all.sh on v* tags via publish.yml.
  • scripts/dashboard/ -- local observability dashboard (ijfw dashboard start)
  • docs/ -- README, DESIGN.md

Key Conventions

  • Core skill (ijfw-core/SKILL.md) hard cap: 55 lines. Single source of truth -- supersedes any older 40/51 references in handoff/instructions docs. Currently 54 lines.
  • On-demand skills: hot-load only when triggered, unload when done.
  • Hooks: shell scripts only, deterministic, no LLM calls.
  • MCP server: ≤14 tools (full manifest, history, retirement-review rationale, and cap policy live in mcp-server/TOOLS.md — single source of truth, machine-checkable via scripts/check-mcp.sh). Combine before raise.
  • Startup report: positive framing ONLY. No negatives, no "not found", no diagnostics.
  • Platform rules files: identical core rules, adapted for platform format.
  • All memory storage: plain markdown (hot), SQLite FTS5 (warm), optional vectors (cold).
  • Dashboard (scripts/dashboard/) is a Claude-host-first feature: memory/project panels read from ~/.claude/projects/; cost data aggregates across all platforms (Codeburn, Codex SQLite, Gemini dirs). Non-Claude-only users see populated cost tiles but empty memory panels -- graceful degradation, not a bug. Full platform-agnostic memory surfacing is a future milestone.

Read the full file on GitHub · 90 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 · 90 lines · 1,924 tokens per session scan A f92479832ff3

Subscribe to this mod's changes

ijfw CLAUDE.md is an instructions file published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 11d ago), licensed MIT. It adds 1,924 tokens to every session, about $0.0096 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.

ai-agentsai-codingclaude-codecodexcursordeveloper-tools
Related

Other instructions, from other repositories

superpowers-zh CLAUDE.md

Claude Code instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.

jnMetaCode/superpowers-zh · 2,083 tokens

superpowers-zh GEMINI.md

Gemini CLI instructions for jnMetaCode/superpowers-zh, covering superpowers-zh 中文增强版, 核心规则, 可用 skills and 如何使用.

jnMetaCode/superpowers-zh · 1,105 tokens

spec-kit-zh AGENTS.md

AGENTS.md instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.

loulanyue/spec-kit-zh · 3,968 tokens

Meta_Kim CLAUDE.md

Claude Code instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.

KimYx0207/Meta_Kim · 4,985 tokens

nopua AGENTS.md

Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.

wuji-labs/nopua · 546 tokens

claude-code-blueprint CLAUDE.md

Instructions for faizkhairi/claude-code-blueprint, covering global claude behavior rules, verify-after-complete (mandatory), what to verify depends on what was built, verification mindset and after verification.

faizkhairi/claude-code-blueprint · 3,009 tokens