bootstrap

A repository setup helper for Chamnan, a tool that builds an index describing the files in a codebase. It also measures how much of the code has useful file comments.

In plain words
What is it for?
Use it once when setting up Chamnan in a repository. It can offer to add comments to files without them and records a baseline of the repository's description coverage.
Why use it?
It gives the repository a starting description and shows where missing file comments make the code harder to understand.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/arcticfox2029/chamnan/bootstrap
Any agent
npx skills add ArcticFox2029/chamnan --skill bootstrap
Clone the repo
git clone --depth 1 https://github.com/ArcticFox2029/chamnan

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 790 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.00790
Opus 5 $0.00020 $0.00395
Sonnet 5 $0.00008 $0.00158
Haiku 4.5 $0.00004 $0.00079

Measured 2d ago against content hash 06d86ee2a00e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap 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.

skills/bootstrap/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up chamnan here

Do these in order. Report the numbers as you go; the user should see what changed, not just "done".

1. Build the index

chamnan-map

Read what it printed. The important line is the described percentage.

2. If coverage is under 70%, offer to fix it — do not just report it

A low number is not a complaint about the user, it is the single biggest lever on whether any of this works. The index is built from each file's opening comment; without them it degrades to a list of filenames, which is worth little.

Say plainly what the number means and what you can do about it, then — with the user's go-ahead — dispatch the commenter agent over the files that lack one. That agent runs on a cheap model because "read this file, write one line about it" does not need an expensive one; this is the routing principle the plugin ships with, applied to its own onboarding.

Give the agent the specific file list, not the whole repo, and tell it which language to write in — read language from .chamnan/config.json (default en). The agent writes English unless you name something else, so this has to be passed explicitly.

Mention to the user that the setting exists and that changing it is one sentence: "use Thai for the comments" is enough, and you edit .chamnan/config.json for them. English costs fewer tokens on every session, but that is a default worth overriding for a team that will not read English comments — say the trade-off once and let them choose.

Then run chamnan-map again and show the before/after coverage.

Never edit files for this without asking first. It touches every undocumented file in the repo.

3. Record where things stand

chamnan-report

On a repo with history this prints a weekly trend and marks today. On a fresh one it will say there is not enough history yet — that is correct, not a failure. Say so rather than hiding it.

4. Write the first STATE.md

Create .chamnan/STATE.md with what the user is actually working on right now. Keep it short — this file is injected into every future session, so it is paid for repeatedly.

Read the full file on GitHub · 76 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.

  1. 2d ago First seen · 76 lines · 41 tokens per session scan A 06d86ee2a00e

Subscribe to this mod's changes

bootstrap is a skill published in the GitHub repository ArcticFox2029/chamnan (4 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 790 once invoked, about $0.0002 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.

Related

Other skills, from other repositories