agentmods.dev

ijfw: Instructions file for Claude Code

CLAUDE.md

ijfw CLAUDE.md is an instructions file for Claude Code 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 for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is FerroxLabs/ijfw's own configuration. It tells Claude Code how to work on ijfw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ijfw configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/seandonahoe/dev/ijfw,.

not rated 214repo 2d ago A scan 1,924 tokens original MIT
View source ↗ FerroxLabs/ijfw npmjs.com
Reuse

Borrowing it

Nothing to install: this file belongs to FerroxLabs/ijfw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FerroxLabs/ijfw/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/FerroxLabs/ijfw

Made for: Claude Code.

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/github.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/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 CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ferroxlabs/ijfw/claude-md"><img src="https://agentmods.dev/badge/instructions/ferroxlabs/ijfw/claude-md.svg" alt="Reviewed on agentmods" width="80" 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. 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 $0.01924 $0.01924
Opus 5.5 $0.00770 $0.00770
Sonnet 5.5 $0.00385 $0.00385
Haiku 4.5 $0.00192 $0.00192

Measured 1mo ago against content hash f92479832ff3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

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. 1mo 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 (214 stars, last pushed 2d ago), licensed MIT. It adds 1,924 tokens to every session, about $0.0077 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 2026-08-30.

Claude Codeai-agentsai-codingcodexcursordeveloper-tools
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,384 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens