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/ramboz/jig/explainnpx skills add ramboz/jig --skill explaingit clone --depth 1 https://github.com/ramboz/jigWhat 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 | $0.00173 | $0.05020 |
| Opus 5 | $0.00086 | $0.02510 |
| Sonnet 5 | $0.00035 | $0.01004 |
| Haiku 4.5 | $0.00017 | $0.00502 |
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 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec 065 introduces this skill as jig's on-demand explainer — the third consumer of the shipped lexicon (065-01). The barrier jig is lowering is vocabulary: the artifacts are dense with opinionated jargon (SPIDR, ADR, vertical slice, reconciliation, deviation log, DoR/AC/DoD, frontmatter) and almost none of it is explained where the reader meets it. The hook (065-02) surfaces one-line defs just-in-time; this skill is the strong-handholding escalation — define a term in depth, or translate a whole dense spec/ADR into plain language for a junior.
Like
/jig:clarify,/jig:pr-review, and/jig:arch-review, explain is a judgment skill — it ships no.pyhelper. The only determinism it needs (load the merged lexicon, read the named artifact, resolve the refs it links) Claude runs inline via Read + the 065-01 loader. The plain-language quality is judgment exercised by this prompt, not something a unit test can assert — the same accepted shape as every judgment-only jig skill.
What this skill does
Translates jig's vocabulary and artifacts into plain language for a reader who is new here — a junior, or anyone meeting spec-driven work for the first time. It has three modes, selected by what the argument is:
- Term mode — the argument is a word or short phrase (
/jig:explain reconciliation). The skill returns that term's plain-language definition from the merged lexicon (jig's shippedlexicon.jsonwith the project'sdocs/memory/glossary.mdoverlaid on top — 065-01), plus its example and see-also when present. If the term is not in the lexicon, the skill says so plainly rather than inventing a definition. - Artifact mode — the argument is a path to a spec or ADR
(
/jig:explain docs/specs/062-refactor-workflow/spec.md). The skill produces a fixed-shape, junior-grade walkthrough of that artifact, defining every jig term it uses inline and auto-pulling the ADRs/specs it links so the reader doesn't have to chase references. - Passage mode — the argument is a pasted snippet of jig output that is
neither a single term nor a file path: a review
VERDICT:envelope, a status-board row likeIN_PROGRESS (wt-me), a hook's "Unrecognized references in prompt…" message, aworkflow.pytransition refusal, asession-planblock. The skill scans the snippet for jig terms (defining each inline) and explains what it is and what — if anything — the reader should do. When the snippet carries no jig vocabulary at all, it gives a plain generic read. This is the mode for the most common confusion moment: a reader pastes the thing that stumped them.
All three modes are ephemeral: the output is chat-only. The skill writes nothing
to disk — no --save flag, no appended section, no file mutation. This keeps
the hot path clean (the 055/057 context-cost discipline) and matches the
clarify-Q3 resolution that explain output is always chat-only.
This is a best-effort comprehension floor, not a guarantee the reader will understand everything — the same honest framing as jig's security floor (ADR-0013) and the soft context mechanisms (055/057). The skill surfaces and explains; it does not certify understanding.
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 · 350 lines · 173 tokens per session scan A b62b9f0235bf
explain is a skill published in the GitHub repository ramboz/jig (6 stars, last pushed 3d ago), licensed MIT. It adds 173 tokens to every session and 5,020 once invoked, about $0.0009 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
frappe-lms
Frappe LMS customization guidance for courses, batches, lessons, quizzes, assessments, enrollment, progress, certificates, portals, and learning workflows. Use when work touches Frappe LMS or education/training flows.
baoyu-comic
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
learn
Knowledge compiler. Extracts patterns, decisions, and anti-patterns from completed campaigns and evolve cycles, then compiles them into structured wiki pages that integrate with existing knowledge rather than appending isolated files. Implements flush→compile→lint pipeline. Auto-triggered by /postmortem and /evolve…
zapier-demo
Walk a new user through setting up their first Zapier action and running it live — the smallest possible win. Asks what app they use, recommends one read action to enable, guides them to mcp.zapier.com to add it, then demonstrates it working in the same chat. Use when the user asks "show me how Zapier works", "set up…
logical-thinking
Determine what follows from explicit premises, rules, evidence, documentation, or observations by selecting and executing the appropriate inference structure. Use when validity, entailment, contradiction, causality, probability, explanation, or the exact strength of a conclusion is central. Do not invoke merely to…
learning-coach
中文高级私人学习教练。用户说“开始学习 X”“继续/下一课”“学完了”“记录进度/打卡”“我学到哪了/还要多久”，正在通过真实项目、源码、作品、题目或任务学习编程、Agent、写作、语言、考试、研究或职业技能，或对具体概念和材料连续追问时使用。触发后主动读取学习现场、学习记录、进度、用户背景和真实材料，替用户选择最近发展区与入口，一次只给一个动作或问题，并用解释、实践、反馈和迁移证据推进掌握。不要让用户先设计课程、选择材料或填写长问卷；只有方向取舍本身尚未解决且会造成明显浪费时，才交给 focus-coach。.