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/git-plm/parts/claude-mdgit clone --depth 1 https://github.com/git-plm/partsWrote 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/git-plm/parts/claude-md)<a href="https://agentmods.dev/instructions/git-plm/parts/claude-md"><img src="https://agentmods.dev/badge/instructions/git-plm/parts/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 | $0.01512 | $0.01512 |
| Opus 5 | $0.00756 | $0.00756 |
| Sonnet 5 | $0.00302 | $0.00302 |
| Haiku 4.5 | $0.00151 | $0.00151 |
Grade A, and why
parts 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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
A KiCad parts library that is stored as data, not code. The CSV files in
database/ are the database — GitPLM
reads them directly and serves them to KiCad over the
HTTP libraries API:
database/g-XXX.csv -> gitplm http (port 7654) -> KiCad
There is no build step and no database to regenerate. gitplm http watches
database/ and reloads on save, so a CSV edit is live in KiCad immediately — no
restart, no library refresh.
The older CSV -> SQLite3 -> ODBC -> KiCad path (parts_db_create in
envsetup.sh, database/#gplm.kicad_dbl, database/parts.sqlite) is obsolete
and kept only for anyone who has not migrated. parts.sqlite is generated and
gitignored. Do not rebuild it unless the user says they are still on that path.
The category triad
A part's three-letter category code (RES, ICS, DIO, ...) names three files
at once, and keeping them aligned is the point of the scheme:
| Concern | Path |
|---|---|
| Data | database/g-XXX.csv |
| Symbols | symbols/g-XXX.kicad_sym |
| Footprints | footprints/g-XXX.pretty/ |
Adding a category means adding a database/g-XXX.csv; gitplm http discovers
it on the next reload. There is no library list to register it in.
Column sets differ per category and are not in a consistent order — always
head -1 the file before writing a row. A few categories (ASY, CBL, ENC,
FAN, FST) are BOM-only and have no Symbol/Footprint columns.
IPNs are CCC-NNNN-VVVV and are the database key. partnumbers.md is the full
specification.
Commands
# Validate a CSV: column counts, IPN sort order, duplicate IPNs, and whether
# Symbol/Footprint references resolve on disk. Run from the repo root.
.claude/skills/adding-parts/scripts/check-csv.py --new-only database/g-reg.csv
# Serve the database to KiCad; watches database/ and reloads on save.
gitplm http
# Markdown formatting (prettier pinned by .prettier-version)
. envsetup.sh && parts_format # write
. envsetup.sh && parts_format_check # check only
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.
- 4d ago First seen · 125 lines · 1,512 tokens per session scan A 23a8345f639a
parts CLAUDE.md is an instructions file published in the GitHub repository git-plm/parts (58 stars, last pushed 7d ago), licensed MIT. It adds 1,512 tokens to every session, about $0.0076 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
firmware CLAUDE.md
Claude Code instructions for OpenIPC/firmware, covering claude.md, what this is, before you start: is this the right repository?, build and common tasks.
Tutorial_AwesomeModernCPP AGENTS.md
AGENTS.md instructions for Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP, covering agents.md, 这是什么, 通用 essentials(所有 agent 必读) and 你来做什么?(按场景路由).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
AMD-BC-250-Windows-Driver AGENTS.md
Instructions for Keshas-dev/AMD-BC-250-Windows-Driver, covering amd bc-250 windows driver — agent notes, host machine, ⚠️ historical-data caution (2026-08-21, strengthened), fresh re-verifications (current build, 2026-08-21) and workspace boundary.
Nothan-OS CLAUDE.md
Instructions for Vinalinux-Org/Nothan-OS, covering claude.md — nothanos, hard rules, toolchain, driver and design philosophy.