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/kaelingraf/redraft/claude-mdgit clone --depth 1 https://github.com/KaelinGraf/redraftWrote 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/kaelingraf/redraft/claude-md)<a href="https://agentmods.dev/instructions/kaelingraf/redraft/claude-md"><img src="https://agentmods.dev/badge/instructions/kaelingraf/redraft/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 5.1 | $0.00768 | $0.00768 |
| Opus 5 | $0.00384 | $0.00384 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
redraft CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
redraft (engine)
This repo is the engine: the MCP server, canonical-store/index code, and the CLI
(redraft serve, redraft init) that redraft ships. It holds no graph data itself —
a project's graph (its nodes, decisions, and the organizing protocol as that
project's own CLAUDE.md) lives in a separate repo, born with redraft init (see
README.md's Quickstart). Engine and graph are cloned, versioned, and upgraded
independently; redraft's own dogfood graph lives in its own sibling repo, not here.
.mcp.json is gitignored in this repo — it is device-specific dev config. To work on
the engine with live MCP tools, write your own pointing at your own graph:
{"mcpServers": {"redraft": {"command": "uv",
"args": ["run", "--directory", "${CLAUDE_PROJECT_DIR:-.}", "redraft", "serve"],
"env": {"REDRAFT_DIR": "<abs path to your graph repo>", "PYTHONPATH": ""}}}}
Running tests
env -u PYTHONPATH uv run pytest -q
-u PYTHONPATH matters on any shell where something else (e.g. a ROS workspace) has
polluted PYTHONPATH — an inherited entry can shadow this project's own dependencies or
autoload an incompatible pytest plugin. Python itself is uv-managed (.python-version
pins 3.12); a system/distro Python is not supported — redraft.server fails fast at
startup if its sqlite3 build lacks FTS5 or extension-loading, both of which a
python-build-standalone/uv-managed CPython provides and many system Pythons don't.
Rebuilding the UI
frontend/ (Vite + React + TypeScript) is dev-time only — not packaged, not under src/.
Its build output is committed under src/redraft/ui/static/ instead, so git clone && uv sync never needs Node/npm (s6-ui.md §7). After any frontend/src/** change:
cd frontend && npm ci && npm run build:ship
build:ship (a package.json script) runs tsc -b && vite build, then replaces
src/redraft/ui/static/ with the fresh frontend/dist/ output. Commit the resulting
src/redraft/ui/static/ changes in the same change as the frontend/ edit that produced
them — frontend/node_modules/ and frontend/dist/ are gitignored; src/redraft/ui/static/
is not.
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 · 61 lines · 768 tokens per session scan A 863c4eeba986
redraft CLAUDE.md is an instructions file published in the GitHub repository KaelinGraf/redraft (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 768 tokens to every session, about $0.0038 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
adc AGENTS.md
Instructions for dbrattli/adc, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
pycontextify AGENTS.md
AGENTS.md instructions for tbrandenburg/pycontextify, covering 1. objective, 2. improvement process, 3. testing strategy, system and integration tests and business-critical unit tests.
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
Waggle-mcp AGENTS.md
AGENTS.md instructions for Abhigyan-Shekhar/Waggle-mcp, covering repository agent rules, custom rules and waggle automatic memory.
sagemath-mcp CLAUDE.md
Instructions for XBP-Europe/sagemath-mcp, covering claude.md, project, commands, linting and testing.
anywidget-mcp AGENTS.md
Instructions for peter-gy/anywidget-mcp, covering anywidget-mcp, commands, architecture, dependency rule and state invariant.