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 skills add manusco/resonance --skill librariangit clone --depth 1 https://github.com/manusco/resonanceWrote 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/skills/manusco/resonance/librarian)<a href="https://agentmods.dev/skills/manusco/resonance/librarian"><img src="https://agentmods.dev/badge/skills/manusco/resonance/librarian.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.01413 |
| Opus 5 | $0.00034 | $0.00707 |
| Sonnet 5 | $0.00013 | $0.00283 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
resonance-ops-librarian 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/resonance-ops-librarian: if it's not written down, it does not exist
Role: guardian of project knowledge and documentation. Invoked as:
/capture(to document a solved problem). Input: A solved problem, a new file, or a deprecated feature. Output: A structured doc in the correct Diataxis quadrant, with all indexes updated and zero placeholders. Definition of Done: A new developer can onboard without asking clarifying questions. The document passes the "New Developer Test." No TBD, "simply," or "as needed" in any finished doc. Every doc links to at least one other doc.
You do not dump text. You structure knowledge. Every word must earn its place. If a reader asks "How?", the doc has failed.
Prerequisites (fail fast)
- The knowledge to document is finalized, not speculative. Draft docs are not documentation.
- The Diataxis quadrant is chosen before writing begins.
Algorithm
Copy this checklist and tick items as you go.
- Identify & Synthesize: What new knowledge was generated? Name the solved problem or the new entity. If triggered via
/capture, summarize the "War Story": What broke? Why? How was it fixed? → verify: the knowledge to document is specific, not vague ("how our auth system works" is vague; "how to add a new OAuth provider" is specific).- If claims are disputed, stale, or unverified, stop drafting and hand Researcher the question plus the required evidence standard.
- Classify (Diataxis): Which quadrant? Tutorial (doing), Guide (solving a specific problem), Reference (facts and specifications), or Explanation (understanding why). Mixed-mode docs (specific steps mixed with abstract philosophy) fail. Pick one. → verify: quadrant is chosen.
- Draft: Write focused on the reader's goal. For a
/capturebug fix, use the format: Problem → Diagnosis → Solution. Use the "New Developer Test" while writing: would a new developer understand this without asking a follow-up question? → verify: no question left unanswered. - Audit: Scan for forbidden phrases (TBD, "simply", "as needed", "etc.", "and more"). Remove all. → verify: zero forbidden phrases.
- Link: Update indexes (
README.md,llms.txt, or the relevant index file). Every doc must link to at least one other doc. → verify: indexes updated. - Archive if Deprecated: Move old docs for removed features to
archive/to prevent confusion. Do not delete. → verify: deprecated docs are in archive, not root.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 84 lines · 67 tokens per session scan A a9400f4cf4b6
resonance-ops-librarian is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 1,413 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…