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.
git clone --depth 1 https://github.com/athola/claude-night-marketWrote 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/commands/athola/claude-night-market/skill-library)<a href="https://agentmods.dev/commands/athola/claude-night-market/skill-library"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/skill-library/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.
<a href="https://agentmods.dev/commands/athola/claude-night-market/skill-library"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/skill-library.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00032 | $0.00676 |
| Opus 5 | $0.00016 | $0.00338 |
| Sonnet 5 | $0.00006 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
skill-library 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 7d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attune Skill Library Command
Build (or rebuild) a project skill library under .claude/skills/
so junior engineers and Sonnet-class models can carry the project
forward: debug it, extend it, validate it, and advance it at the
departing expert's standard.
When To Use
Use this command when you need to:
- Package a repository's institutional knowledge before the person or session holding it moves on
- Bootstrap
.claude/skills/in a repo that has none - Re-run discovery and review over a drifted project library
When NOT To Use
Avoid this command if:
- You are authoring or improving a single skill (use
/abstract:create-skill) - The skills belong inside a plugin, not the project (use
Skill(plugin-dev:skill-development)) - You only want an audit of existing skills (use
/abstract:skills-eval)
Usage
# Full mission: discover, author, review, report
/attune:skill-library
# Resume an interrupted mission from .attune/mission-state.json
/attune:skill-library --resume
# Constrain the library size (default: adapt within 10-16)
/attune:skill-library --max-skills 12
What This Command Does
- Invokes
Skill(attune:skill-library-mission)and creates a custom mission in.attune/mission-state.jsonwith phasesdiscover, author, review, report - Discover: investigates the repo like an incoming principal engineer, then asks the user at most five questions the repo cannot answer
- Author: dispatches one authoring agent per skill from the
adapted taxonomy, each carrying the non-negotiable authoring
rules and a write fence limited to
.claude/skills/ - Review: runs factual, doctrine, and usability reviewers in parallel, then one fixer applying blocking and important findings
- Report: delivers the skill inventory, spot-check evidence, and remaining uncertainties
Arguments
| Argument | Description |
|---|---|
--resume |
Continue from saved mission state |
--max-skills <n> |
Cap the adapted taxonomy at n skills |
--skip-questions |
Proceed with repo evidence only; record assumptions in mission state |
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.
- 7d ago First seen · 85 lines · 32 tokens per session scan A 7a74b5eb24d2
skill-library is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 676 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 2026-09-03.
Other commands, from other repositories
contact-upsert
Create or update a contact, optionally assign to groups.
github-issue-fix
This is a detailed way you can analyze the GitHub issues and let Claude handle them in best possible way.
spec
A requirements-planning command for OpenSpec, a tool that records software changes as proposals, specification updates, and task lists. It clarifies the request, challenges risky assumptions, and pauses for approval before implementation.
start
Analyze this project and build a GoalT goal tree for it, linking real files and backend artifacts to each goal.
features:status
(Features) Show implementation status by phase.
features:add
(Features) Add a new feature to a specific phase.