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/sentasity/cadence/c-explainnpx skills add sentasity/cadence --skill c-explaingit clone --depth 1 https://github.com/sentasity/cadenceWrote 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/sentasity/cadence/c-explain)<a href="https://agentmods.dev/skills/sentasity/cadence/c-explain"><img src="https://agentmods.dev/badge/skills/sentasity/cadence/c-explain.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 | $0.00159 | $0.02075 |
| Opus 5 | $0.00079 | $0.01038 |
| Sonnet 5 | $0.00032 | $0.00415 |
| Haiku 4.5 | $0.00016 | $0.00208 |
Grade A, and why
c-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 4d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/c-explain
You run an interactive discussion of an existing design or plan. The user drives the questions; you ground answers in the doc and the code under it. You never critique (that's /c-check), never hunt defects (that's /c-find-bugs), and never write a new design or plan.
Invocation forms
/c-explain <design-folder-path>— whole design./c-explain <plan-folder-path>— whole plan./c-explain <single-doc-path>— one child doc in isolation./c-explain <doc-path>#<heading>— sub-section anchor (heading slug or H2/H3 title)./c-explain --any <path>— bypass the Cadence-layout check for imported/external docs.
Entry contract
Refuses when: the target does not resolve to an artifact; OR the target is in a Cadence-managed location and the resolved artifact lacks the expected structure (no overview, missing frontmatter) — check existence and structure via skills/_shared/storage-resolution.md (artifact_exists) in the active backend — unless --any is set.
Phase 1 — Parallel context scan
Before the first user question, all in parallel:
- Read the target doc(s) via
skills/_shared/storage-resolution.md(read_artifact). For a folder target, read the overview + all child docs; for a section anchor, scope to that section but still load the parent doc's frontmatter for context. Do not assume apaths.designs/paths.plansfile path. - Resolve config by running
node "${CLAUDE_PLUGIN_ROOT}/scripts/resolve-config.js"and use its JSONconfig(paths, naming, advisor list); contract inskills/_shared/config-resolution.md; never read config files directly. - Extract File Map references from the doc(s) — note which code files are claimed to exist under this design's implementation.
git log -20 --oneline -- <slug-or-paths>to surface recent changes touching the design's area.- Read the repo's
CLAUDE.mdif any.
The scan is invisible — it sharpens the orientation, doesn't produce a report.
Phase 2 — Orientation (one screen)
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.
- 4d ago First seen · 126 lines · 0 tokens per session scan A d3a09a82ae6a
c-explain is a skill published in the GitHub repository sentasity/cadence (1 stars, last pushed 10d ago), licensed MIT. It adds 159 tokens to every session and 2,075 once invoked, about $0.0008 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
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.