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/manusco/resonance/explainnpx skills add manusco/resonance --skill explaingit clone --depth 1 https://github.com/manusco/resonanceWhat 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 | $0.00113 | $0.01585 |
| Opus 5 | $0.00056 | $0.00792 |
| Sonnet 5 | $0.00023 | $0.00317 |
| Haiku 4.5 | $0.00011 | $0.00159 |
Grade A, and why
resonance-ops-explain 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/explain: keep the operator learning when the agent writes the code
Role: the teacher of the human in the loop. Input: a concept, a diff or PR, an idea, or a window of recent work, plus who is reading and what they already know. Output: a dense, concrete explainer written for this developer; optionally a predict-then-reveal check-in. Definition of Done: the reader can re-explain the thing in their own words. If they already could, the explainer taught nothing and should have been shorter or skipped.
The Ratchet keeps the project from going hollow: memory, tests, and the ledger compound so the codebase gets smarter. This skill keeps the operator from going hollow. When the agent writes the code, the human stops getting the understanding that writing it by hand used to supply for free. An explainer is the counterweight, so the next decision the person makes is still theirs.
What this is not
- Not documentation for the repo. The librarian (
/capture) writes for the codebase's future readers; this writes for one person, now. - Not a summary. A summary compresses what happened. An explainer builds a model the reader did not have.
- Not a textbook. It is grounded in this code, this change, this reader. A generic explanation that could have been written without opening the repo has failed.
Modes
Pick the mode from the request:
- Concept: a pattern or idea new to this codebase ("how does the new job queue work"). Teach the idea, then show where it lives here and why it was chosen.
- Diff / PR: a specific change ("explain what this PR does"). Walk the change by intent, not line by line: what problem, what moved, what to watch.
- Idea: a proposal or direction ("explain the plan for auth"). Make the shape and the tradeoffs legible.
- Recent work: a window of the developer's own recent sessions ("what did we build this week"). Reconstruct the thread so they own it again.
The explainer craft
- Write for one reader. Name their level and what they know; teach from there, not from zero.
- Concrete over abstract. Use the real names: this file, this function, this number. An example from the actual change beats a generic one.
- Dense and visual. A diagram, a before and after, a small table earns its space. Prose walls do not.
- Choose the visual form that matches the idea. Use a call tree for runtime flow, a component tree for UI structure, a state flow for lifecycle logic, a file map for ownership, a data-flow diagram for movement across boundaries, a diff sketch for before and after, or one small HTML visual only when static text cannot make the model clear.
- One model per explainer. Teach the single load-bearing idea well; do not tour the whole system.
- End where understanding is testable: the reader could now predict what breaks if this changed.
What ships with it
5 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.
- 3d ago First seen · 76 lines · 113 tokens per session scan A 4801e82c3aee
resonance-ops-explain is a skill published in the GitHub repository manusco/resonance (37 stars, last pushed 3d ago), licensed MIT. It adds 113 tokens to every session and 1,585 once invoked, about $0.0006 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
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
obsidian-to-clew-import
Convert an Obsidian vault or wiki-linked markdown graph into a validated structured-learning graph package for Clew. Use when the user wants to inspect a vault, preview whether it imports cleanly, preserve explicit relation markers, choose only the few import settings that matter, and produce a fail-closed package…