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/alexmond/alexmskillsWrote 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/alexmond/alexmskills/library)<a href="https://agentmods.dev/commands/alexmond/alexmskills/library"><img src="https://agentmods.dev/badge/commands/alexmond/alexmskills/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/alexmond/alexmskills/library"><img src="https://agentmods.dev/badge/commands/alexmond/alexmskills/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 | $0.00017 | $0.00774 |
| Opus 5.5 | $0.00007 | $0.00310 |
| Sonnet 5.5 | $0.00003 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
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 1mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prompt-coach:library
Look up the closest gold-standard prompt template from Anthropic's Claude Code Prompt Library for a task you describe — turning the coach from corrective ("here's what's wrong with your prompt") into generative ("here's the canonical prompt for what you want to do"). Offline: matches against a vendored snapshot, no network at call time.
What to do
-
Resolve
scripts/config.pyfrom this plugin's root (the parent of thiscommands/directory), in either client's cache or a dev checkout. -
Route on the argument:
User intent Run "library for <task>" / "show me a prompt for<task>"--json library "<task>""what's in the prompt library?" / no argument --json library(taxonomy)"show the <Category>templates" (Review / Debug / Refactor / …)--json library --category <Category>"prompts for the <role>role" (security / pm / ops / …)--json library --role <role>Always pass
--json(before the verb) and--cwd <repo>. -
A task query → the JSON gives
matches[], each withcat,sdlc,roles,_score, and_filled(the template with its{slots}filled by Anthropic's example values). Present the top 1–3:- Show each template verbatim (it's the copy-paste-ready prompt).
- Note its category / phase / role tags.
- Offer to adapt the top one to the user's actual context (swap the example slot values — file paths, formats — for theirs) and run it.
- Cite the source URL (it's Anthropic's library, vendored with attribution).
-
No query → the JSON gives
count,categories,phases. Summarize the taxonomy (5 SDLC phases, 15 categories) and invite a task lookup.
Notes
- The snapshot lives at
data/prompt-library.json; refresh it withscripts/gen-prompt-library.py(fetches the live docs page). It is Anthropic documentation content, vendored with attribution — not this plugin's work. - Read-only: this never changes config, mastery, or state.
- The
rolesplugin uses--categoryto anchor each persona (e.g.reviewer→--category Review); see the role-system's Prompt Library anchors. - The coach ALSO uses this matcher passively: when a rule fires and
library_hintsis on (default), the collaborator rewrite is grounded in the closest library template's phrasing + slot structure.
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.
- 1mo ago Changed · -1 lines 053b54e89357
- 1mo ago First seen · 63 lines · 17 tokens per session scan A e9d29535f3d8
library is a command published in the GitHub repository alexmond/alexmskills (10 stars, last pushed 12d ago), licensed MIT. It adds 17 tokens to every session and 774 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
discuss
A command that interviews you in five phases and saves a detailed description of a proposed feature or change. EARS is a structured way to write requirements so they can be checked clearly.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
rev
Invoke Code Reviewer for code quality, security, requirements validation, and best practices review.
design-audit
Audit the rendered design of live sites. Evidence capture first, then one critique per site. Argument is a URL, a repo name, or all.