What is headcleaner-cli CLAUDE.md?

Claude Code instructions for the HeadCleaner repository, including coding rules, required development records, testing commands, and documentation checks.

They help agents plan multi-step tasks, trace code, run the required Python tests, maintain backlog and issue records, and avoid claiming unverified review.

They keep changes within the repository, preserve existing work, and require evidence for tests, documentation, and human review status.

How jamesdsizemore/headcleaner-cli configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jamesdsizemore/headcleaner-cli. 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/jamesdsizemore/headcleaner-cli/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jamesdsizemore/headcleaner-cli

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jamesdsizemore/headcleaner-cli/claude-md/github.svg)](https://agentmods.dev/instructions/jamesdsizemore/headcleaner-cli/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jamesdsizemore/headcleaner-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/jamesdsizemore/headcleaner-cli/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jamesdsizemore/headcleaner-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/jamesdsizemore/headcleaner-cli/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 578 This file is loaded in full into every session.

When invoked 578 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.

Model	Per session	Once invoked
Fable 5.1	$0.00578	$0.00578
Opus 5.5	$0.00231	$0.00231
Sonnet 5.5	$0.00116	$0.00116
Haiku 4.5	$0.00058	$0.00058

Measured 2mo ago against content hash d0286c9f14ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

headcleaner-cli 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 2mo 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 · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Repository discipline

Work only inside this repository. Do not commit, push, merge, reset, or rewrite history unless the user explicitly asks.
Preserve existing user work. Inspect Git status before edits; change only the requested scope.
Use RTK for bounded Git/diff evidence, Graft for symbol/caller tracing, and context-mode for plans, contracts, and documentation seams before edits and at final review.
The mandatory test command is unset PYTHONPATH && uv run --no-sync --python 3.13 pytest. Focused runs may append test paths or pytest flags.
Never auto-claim human review of converted output. Preserve status: unverified and verified: human:pending defaults.

Required development records

For every multi-step task, create or update a local plan under .plans/ before implementation. .plans/ is ignored and contains working context only.

Keep these tracked records current during development:

BACKLOG.md — scoped work, acceptance evidence, documentation impact, and non-goals.
ISSUES.md — real defects and recoveries; archive, do not delete.
MEMORY.md — stable repository conventions only; never secrets or transient output.
DEVELOPMENT_HISTORY.md — phase and commit evidence.
DEPENDENCIES.md and PINS.md — dependency intent, compatibility pins, and lock verification.

Non-negotiable documentation gate

“Docs updated” means the entire active documentation surface was considered: root README.md plus every Markdown page under docs/, excluding docs/_archive/ and the historical docs/plans/archive/.

For every phase:

Create an exhaustive audit with uv run --no-sync --python 3.13 python scripts/verify_docs.py --write-audit-template <phase>.
Update every pertinent page. For every remaining page, record reviewed or not-applicable with a concrete evidence statement in docs/development/phase-audits/<phase>.json.
Run uv run --no-sync --python 3.13 python scripts/verify_docs.py --phase <phase>.
Do not state that the phase is complete until the audit, links/anchors, focused tests, full suite, and final Git review pass.

Read the full file on GitHub · 41 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.

2mo ago First seen · 41 lines · 578 tokens per session scan A d0286c9f14ee

Subscribe to this mod's changes

headcleaner-cli CLAUDE.md is an instructions file published in the GitHub repository jamesdsizemore/headcleaner-cli (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 578 tokens to every session, about $0.0023 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 2026-08-31.

headcleaner-cli CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
headcleaner-cli CLAUDE.mdjamesdsizemore/headcleaner-cli	Instructions file	0	2mo ago	Apache-2.0	A	578	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

headcleaner-cli: Instructions file for Claude Code