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/atomchung/fomo-kernel/claude-mdgit clone --depth 1 https://github.com/atomchung/fomo-kernelWhat 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 | $0.00399 | $0.00399 |
| Opus 5 | $0.00199 | $0.00199 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
fomo-kernel 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 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
CLAUDE.md — Claude Code adapter
@AGENTS.md
The line above imports the shared always-on instruction floor. AGENTS.md is
the same floor Codex and other clients read natively, and it carries the route
selection, the non-negotiable boundaries, and the instruction-authority policy
this file is subordinate to. The detailed host-neutral contract for changing
this repository — development discipline, tests, the privacy boundary, commit
and PR conventions, and the mirrored-surfaces map — is
docs/maintainer-guide.md. Read it before editing
repository code; it is not auto-loaded, deliberately.
Edit boundary for this file
A change here must name the Claude-only mechanism it supports. Shared product, architecture, test, privacy, issue, PR, or runtime guidance belongs in the shared authority.
This file is a host adapter, so the authority policy in AGENTS.md applies to
it: it may change tool mechanics only. Keep it short —
tests/test_doc_language.py fails the suite if it outgrows its line budget or
if a shared section heading comes back into it.
Claude Code hooks
Committed hooks in .claude/ enforce the test gate. Hook if: filters have
been observed to be unreliable in the supported Claude Code setup. Every hook
script must inspect tool_input.command from stdin and exit immediately for
unrelated commands. Follow the self-filtering pattern in
pre_commit_test_gate.sh.
That gate is the mechanical half of a shared rule and it exists only here.
Since #492 it covers repository integrity (tests/test_repo_hygiene.py), not
the whole registry: behaviour is gated by the blocking product-contract CI
job before merge. The rule itself is stated in AGENTS.md for every client
precisely because no other client enforces it.
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 · 38 lines · 399 tokens per session scan A 4908633c6c56
fomo-kernel CLAUDE.md is an instructions file published in the GitHub repository atomchung/fomo-kernel (9 stars, last pushed 3d ago), licensed MIT. It adds 399 tokens to every session, about $0.0020 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 2026-08-31.
Other instructions, from other repositories
AI-WealthPilot AGENTS.md
Instructions for Michelia-L/AI-WealthPilot, covering ai wealthpilot — agent guide, 工作原则, 架构约定（最重要）, 常用命令 and 后端（仓库根目录）.
deltalytix AGENTS.md
AGENTS.md instructions for hugodemenez/deltalytix, covering agents.md, package manager, self-host quickstart (dashboard bypass mode), build and test commands and bun run test:e2e:rithmic.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.