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/rishi4792/compass/explainnpx skills add Rishi4792/compass --skill explaingit clone --depth 1 https://github.com/Rishi4792/compassWhat 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 | $0.00066 | $0.00509 |
| Opus 5 | $0.00033 | $0.00254 |
| Sonnet 5 | $0.00013 | $0.00102 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
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 2d 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.
What it actually says
compass:explain
Teach, don't just answer. This skill gives a genuine, plain-English walkthrough — big picture first, one piece at a time, an analogy and a concrete example before any jargon.
Do this now: read plugins/compass/shared/walkthrough.md — it owns the teaching method, and it ships with this plugin so it is present on every install. Then frame the walkthrough to the request:
Optional enhancement, with a fallback: if a richer walkthrough skill is installed at user level, you may also invoke the Skill tool with skill: feynman-walkthrough to produce a durable explainer the person can revisit. If it is not installed, do not stop and do not mention it — shared/walkthrough.md is the method and the explanation is just as good; what is lost is the saved artefact, not the teaching. Compass does not ship that skill, and for three releases this stage pointed at it with no fallback, which meant the teaching surface worked only on its author's machine.
- "How does Compass work?" → teach the mental model: contract-first, then the assembly-line-with-gates (contract → review → plan → review → build → review → ship), why each gate is a real script check, and how nothing advances until it proves it matches the locked contract.
- "Explain this build to me / to a stakeholder." → read the active build's state (
compass.sh state-root→ itscontract.md/progress.md/plan.md/receipts.md/review-ledger.md) and walk through what it's building, where it stands, what the reviews caught, and what's next — pitched at the audience (engineer vs. non-technical stakeholder). Offer to render the visual Contract Brief / Cockpit viacompass-visualas the accompanying picture.
Match the depth to the ask: a 60-second orientation, or a full guided walkthrough. This teaches; it never changes build state or advances a stage.
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.
- 2d ago First seen · 19 lines · 66 tokens per session scan A d20d29d4c5bc
explain is a skill published in the GitHub repository Rishi4792/compass (2 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 509 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 2026-08-31.
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…