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 skills/baodq97/open-plugin/chomnpx skills add baodq97/open-plugin --skill chomgit clone --depth 1 https://github.com/baodq97/open-pluginWhat 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 | $0.00149 | $0.02949 |
| Opus 5 | $0.00075 | $0.01474 |
| Sonnet 5 | $0.00030 | $0.00590 |
| Haiku 4.5 | $0.00015 | $0.00295 |
Grade C, and why
chom scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`rm -rf`). How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chom — install a skill from GitHub
chom clones a skill from a GitHub URL, copies only that skill folder into
the user's personal skills directory (~/.claude/skills/), and — only when the
user explicitly asks — rewrites its description for better auto-triggering.
Core invariant — never break this
The whole skill boils down to three steps that must happen in this exact shape:
- Clone the repo into a throwaway temp dir (
mktemp -d). Never clone into~/.claude/skills/, never clone into the current working directory. - Copy only the one skill folder out of that temp dir into
~/.claude/skills/<skill-name>/. Never copy the surrounding repo, README, sibling skills,.git/, CI files, or anything else. - Delete the temp dir. Every path, even on failure. Use a
trapso the cleanup survives Ctrl-C and aborts.
If you find yourself about to copy more than the skill folder, stop and re-read this section.
When to use
Trigger on any of:
chom <url>or/chom <url>- "install this skill from github", "add this skill", "import this skill", "grab this skill", "pull this skill"
- A bare GitHub URL that clearly points at a folder containing
SKILL.md
If the URL comes without an explicit verb, confirm intent before cloning — don't install something the user didn't ask for.
Where skills live
User-scoped skills live at ~/.claude/skills/<skill-name>/.
On Windows + bash that resolves to /c/Users/<user>/.claude/skills/<skill-name>/.
Never install outside that directory. Project-scoped skills and plugin skills
live elsewhere and chom doesn't own those.
URL shapes you must handle
| URL shape | Action |
|---|---|
github.com/OWNER/REPO/tree/REF/PATH |
Clone OWNER/REPO at REF, copy PATH/ |
github.com/OWNER/REPO/blob/REF/PATH/SKILL.md |
Strip filename, copy parent folder |
github.com/OWNER/REPO (no path) |
Clone repo, then ask user which folder |
Ends with .git |
Clone directly, ask for a subpath if one isn't obvious |
A branch / tag / commit hash in the REF slot |
Pass it to --branch; for commit SHAs you'll need a non-shallow clone, see Edge cases |
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 · 272 lines · 149 tokens per session scan C b8f56e896aad
chom is a skill published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 149 tokens to every session and 2,949 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
meta-synthesis
Reads /context/skill-sessions.md (the session log every execution skill writes to) to detect patterns that repeat across 2+ sessions, proposes new guardrails for /context/meta-patterns.md, and proposes brain updates for confirmed learnings. Run on-demand or roughly weekly — not a scheduled background job. Trigger on…
meta-learn
Deliberate deep-dive capture for a completed skill session that deserves more than the automatic one-line row every T1/T2 skill already logs at its own close — asks three extraction questions (what surprised you, what was wrong, what was missing), turns real answers into specific, falsifiable pattern statements, and…
new-course
Build a whole course on a subject, from scratch, on disk. A light survey of the domain, then the placement-quiz decision, then a deep multi-agent research pass that becomes an ordered taxonomy, a table of contents grouped into books and chapters, and a course folder that teaches itself. Use when the user asks for a…
self-assess
Placement quiz that finds someone's real level in a subject and writes it to PROFILE.md. Scenario questions in small batches, never definitions, with neutral options that cannot be eliminated by tone, plus self-report checks that separate knowing a word from being able to act on it. Use when the user asks to measure…
learn
The way into learnable and the way back. If a course already exists here it continues from exactly where the learner stopped, next lesson, next chapter, no re-planning. If nothing exists yet it asks whether to measure their level first or go straight to building a course. Use when the user says they want to learn…
new-book
Write the next book of the course: its chapters and every lesson inside them, ready to teach. Reads the plan, runs a short research pass only for chapters that need one, then writes one file per chapter with the opening question, the correction, the explanation, the terms with their origins, and the end-of-chapter…