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/jamesdsizemore/headcleaner-cli/agents-mdgit clone --depth 1 https://github.com/jamesdsizemore/headcleaner-cliWhat 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 | $0.02915 | $0.02915 |
| Opus 5 | $0.01458 | $0.01458 |
| Sonnet 5 | $0.00583 | $0.00583 |
| Haiku 4.5 | $0.00292 | $0.00292 |
Grade A, and why
headcleaner-cli 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.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file orients AI coding agents working in this repo.
What is headcleaner?
A Python CLI that walks a folder and converts every supported document
into Markdown and/or OKF v0.2 with frontmatter. Companion linter
(headcleaner lint) reviews the converted output. Built with an
omp-inspired TUI in a neon cyan/pink/purple palette.
The lightning-bolt jar is the brand mark.
Stack
- Language: Python 3.12 (pinned in
.python-version) - Package manager: uv (creates
.venv/, manages deps frompyproject.toml) - TUI: Textual + custom
theme.py(rounded box-drawing, powerline separators, neon palette) - Office engine:
officeclibinary (single binary on PATH; npm-installable:npm i -g @officecli/officecli) - Output formats: Markdown (with YAML frontmatter), OKF v0.2 (with full trust family), or both
- Linter:
headcleaner lint— review converted MD/OKF for formatting issues
Commands
uv sync # install all deps into .venv
uv run headcleaner --help # CLI help
uv run headcleaner convert IN --output OUT # convert a folder
uv run headcleaner lint OUT # review converted output
unset PYTHONPATH && uv run --no-sync --python 3.13 pytest # required test gate
uv run python -m headcleaner.cli # same as `headcleaner`
Layout
src/headcleaner/
__init__.py
cli.py # Click entrypoint (headcleaner command)
tui.py # Textual TUI
theme.py # ANSI colors + box-drawing symbols
walk.py # folder walker
router.py # ext → engine dispatch
normalize.py # adapter output → CanonicalDoc
run.py # pipeline orchestrator
lint.py # post-conversion linter
engines/
base.py # Adapter ABC
officecli.py # DOCX/XLSX/PPTX
pdf.py # PDF (pdfplumber, opt-in pytesseract)
html.py # HTML/HTM (BeautifulSoup + markdownify)
txt.py # TXT (chardet)
emit/
markdown.py # write .md with lightweight frontmatter
okf.py # write OKF v0.2 concept
okf_index.py # per-directory index.md
manifest.py # run-level manifest.json
tests/ # pytest suites
conftest.py # shared fixtures
test_walk.py
test_router.py
test_normalize.py
test_emit.py
test_run.py
test_lint.py
fixtures/
sample.xlsx # hand-rolled valid XLSX
docs/ # active user/developer/maintainer docs plus development audits
scripts/
verify.sh # post-install sanity check
install.sh # macOS / Linux / WSL one-line installer
install.ps1 # Windows PowerShell installer
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 · 219 lines · 2,915 tokens per session scan A 4a317a0a44fe
headcleaner-cli AGENTS.md is an instructions file published in the GitHub repository jamesdsizemore/headcleaner-cli (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,915 tokens to every session, about $0.0146 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
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).
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.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.