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/doodledood/manifest-dev/claude-mdgit clone --depth 1 https://github.com/doodledood/manifest-devWrote 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.
[](https://agentmods.dev/instructions/doodledood/manifest-dev/claude-md)<a href="https://agentmods.dev/instructions/doodledood/manifest-dev/claude-md"><img src="https://agentmods.dev/badge/instructions/doodledood/manifest-dev/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.05523 | $0.05523 |
| Opus 5 | $0.02762 | $0.02762 |
| Sonnet 5 | $0.01105 | $0.01105 |
| Haiku 4.5 | $0.00552 | $0.00552 |
Grade A, and why
manifest-dev 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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
manifest-dev marketplace — manifest-driven workflows for Claude Code. /define interviews and writes a Manifest; /do executes it and evaluates every Acceptance Criterion and Global Invariant under a run-level verification mode. Ships skills, not custom agents.
Public Repository Discipline
This repo is public. Everything committed or posted to it — docs, ADRs, READMEs, PR titles and descriptions, commit messages, issue text — must stand on its own merits. Keep out what a reader would be worse off for seeing: credentials and secrets, the contents of private planning or strategy documents, anything personal, and links into chat sessions or transcripts nobody outside can open. Also skip commentary on the repo's own adoption or popularity (star counts, usage levels, traction) — a positioning choice, not a secrecy one.
Set the bar there and no lower. Incidental working detail is fine and not worth policing: a branch name, a local path, the name of a workflow mode, a note on how a change was produced. Treating those as exposure costs more than it protects. ADRs state decisions with their technical grounds, not the deliberation history behind them. Temporary ops documents are allowed when clearly marked, but must read as neutral, forward-looking operations content.
Development Commands
# Lint, format, typecheck, test
ruff check --fix claude-plugins/ tests/ && black claude-plugins/ tests/ && mypy && python3 -m pytest tests/
# Test plugin locally
/plugin marketplace add /path/to/manifest-dev
/plugin install manifest-dev@manifest-dev
tests/ asserts properties of the shipped prompts themselves — that gate examples use the current
schema, that mode mechanics stay out of the spine, that the bare-name distributions carry the
qualifier strip their sync rules require. Adding a skill, a dimension, or a distribution can
therefore turn the suite red without any Python changing, and that red is the signal working as
intended.
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.
- 5d ago First seen · 256 lines · 5,523 tokens per session scan A 1947a829725a
manifest-dev CLAUDE.md is an instructions file published in the GitHub repository doodledood/manifest-dev (72 stars, last pushed 5d ago), licensed MIT. It adds 5,523 tokens to every session, about $0.0276 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
lid AGENTS.md
Instructions for jszmajda/lid, covering agents.md, repository purpose, structure, plugin architecture (claude code) and other agentic coding tools.
mach10 CLAUDE.md
Instructions for LeanAndMean/mach10, covering claude.md, project overview, architecture, command structure and key design decisions.
catalyst AGENTS.md
AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.
RedEye CLAUDE.md
Instructions for Bitmia-ai/RedEye, covering redeye, commands, how it works, control files and architecture.
catalyst CLAUDE.md
Claude Code instructions for coalesce-labs/catalyst, covering claude code, loading & invocation, orchestration runtime, pull request review (codex) and code understanding (serena mcp).
claude-sdlc CLAUDE.md
Claude Code instructions for lantisprime/claude-sdlc, covering claude.md, what this repo is, design intent — read this before "improving" anything, eat your own dog food and hook strictness philosophy.