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.
npx agentmods add instructions/ferroxlabs/ijfw/agents-mdgit clone --depth 1 https://github.com/FerroxLabs/ijfwWhat 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 | $0.05150 | $0.05150 |
| Opus 5 | $0.02575 | $0.02575 |
| Sonnet 5 | $0.01030 | $0.01030 |
| Haiku 4.5 | $0.00515 | $0.00515 |
Grade A, and why
ijfw AGENTS.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 2d 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.
What it actually says
AGENTS.md
This file follows the open AGENTS.md spec (https://agents.md/) and is the canonical agent-instructions surface for this project. Platform-specific files (CLAUDE.md, GEMINI.md, WAYLAND.md, codex/AGENTS.md, .cursorrules, .windsurfrules, copilot-instructions.md) are thin adapters that point here.
Four IJFW-managed regions live in this file. Content outside the markers is yours -- IJFW will never touch it.
Project memory at .ijfw/memory/. Call ijfw_memory_prelude for full context.
Last handoff: IJFW 1.3.2 RC audit/verify pass is complete locally. The 1.3.1 release caution still applies: user explicitly said, "When windows completes and verifies we go forward. Remember that". Do NOT create/push tags or attempt npm publish until Windows CI/release clearance is explicitly given by the user. Current 1.3.2 verification has passed 880/880 Node tests, 158/158 focused regression tests, package dry-runs, temp-project swarm E2E, cross-audit reconciliation, platform drift, diff hygiene, and preflight blocking gates. Findings fixed during audit: hermetic update-confirm npm test PATH, Trident EPIPE hardening, workflow bootstrap/fallback guidance, team/AGENTS mirroring specificity, Codex dispatch command order, and memory/release-gate consistency. Advisory warnings only: eslint-security non-literal fs warnings in installer paths and PSScriptAnalyzer skipped because pwsh unavailable locally. No tag or publish performed.
No project agents yet. Run ijfw team to set them up.
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.
- 2d ago First seen · 694 lines · 5,150 tokens per session scan A 6a10e0376bc2
ijfw AGENTS.md is an instructions file published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 9d ago), licensed MIT. It adds 5,150 tokens to every session, about $0.0258 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 instructions, from other repositories
superpowers-zh GEMINI.md
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.
memorix CLAUDE.md
Instructions for AVIDS2/memorix, covering memorix - agent instructions for claude code, using memorix memory tools, when to search memory, when to store memory and when to resolve memory.
specops CLAUDE.md
Instructions for sanmak/specops, covering claude.md, what is specops, build & validate commands, run all tests (single command) and generate for a single platform.
ReqForge CLAUDE.md
Instructions for zxpmail/ReqForge, a project described as: ReqForge — From requirements to shippable products. Open-source Agent Harness for Claude Code, Cursor & OpenCode. Spec→Plan→Build, hooks, review. /change-manager for brownfield.
claude-code-blueprint AGENTS.md
Instructions for faizkhairi/claude-code-blueprint, covering agents.md: repository orientation for ai assistants, what this repo is, what this repo is not, repository layout and how to help the user.
Atomic-Spec AGENTS.md
Instructions for Chappygo-OS/Atomic-Spec, covering agents.md — adding a new ai agent to atomic spec, about atomic spec and the atomicspec cli, general practices, adding new agent support and current supported agents.