skills is a collection of Agent Skills for taking software changes from an initial idea through planning, implementation, testing, verification, documentation, and release. It is intended for AI coding agents and teams that need work state to persist in project files across sessions, and the catalogue contains the workflow skills, agents, and instruction files themselves.
Borrowing it
Nothing to install: this file belongs to jsmastery-pro/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jsmastery-pro/skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/jsmastery-pro/skillsWrote 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/jsmastery-pro/skills/claude-md)<a href="https://agentmods.dev/instructions/jsmastery-pro/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/jsmastery-pro/skills/claude-md/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/instructions/jsmastery-pro/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/jsmastery-pro/skills/claude-md.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 | $0.00582 | $0.00582 |
| Opus 5.5 | $0.00233 | $0.00233 |
| Sonnet 5.5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
skills 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 2mo 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: Engineering Workflow Skills
A collection of Claude Code skills encoding a phase based engineering workflow. No mandated playbook: you run whichever skills a change needs, in whatever order fits. /scope recommends a workflow tier (Prototype/Alpha/Beta/GA, how much verification a project or feature warrants), but it is a default you override per feature, never a forced track.
Conventions every skill follows
- The engineer decides; the AI recommends. Any AI initiated verification or critique (e.g.
/architect's cross model spec check) is offered, never run or skipped on the engineer's behalf. Whatever such a check finds, a gap, a load bearing decision, a fix, is surfaced to the engineer to decide, never silently resolved or auto applied. A check the engineer invokes directly (/check verify,/check review) is already their choice to run, and still reports rather than auto fixes. - Suggestions, never gates. The engineer is in charge: every step after
/develop(/check verify,/test,/check review,/document) is suggested by the tier and freely skippable, anddoneis the engineer's to declare, never a status a skill withholds until boxes are ticked. A skipped step is recorded honestly as skipped. The one thing the workflow asks is that a load bearing decision be written down (a spec); even that is flagged, not enforced (anAssumedspec never blocksdone). - Every user facing question carries exactly one recommended option with a one line why (make the call, let them override). Never a neutral menu, never a cold question, never a silent decision.
- Keep skills lean. A skill loads in full on its path every run, so every line is a recurring cost. Cut lines that don't change the agent's behavior, keep the reasoning in the commit or PR (not the skill body), name concepts instead of explaining them, and split out only rare, long content. Full guidance:
docs/conventions.md. Runnpm run checkbefore committing skill edits.
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.
- 2mo ago First seen · 20 lines · 582 tokens per session scan A 7c3be7aa08a6
skills CLAUDE.md is an instructions file published in the GitHub repository jsmastery-pro/skills (1,602 stars, last pushed 2mo ago), licensed MIT. It adds 582 tokens to every session, about $0.0023 per session on Opus 5.5. 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.
skills CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skills CLAUDE.mdjsmastery-pro/skills | Instructions file | 1.6k | 2mo ago | MIT | A | 582 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |