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/docs-sitenpx skills add sentasity/cadence --skill docs-sitegit 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/docs-site)<a href="https://agentmods.dev/skills/sentasity/cadence/docs-site"><img src="https://agentmods.dev/badge/skills/sentasity/cadence/docs-site.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 | $0.00141 | $0.00805 |
| Opus 5 | $0.00071 | $0.00402 |
| Sonnet 5 | $0.00028 | $0.00161 |
| Haiku 4.5 | $0.00014 | $0.00081 |
Grade A, and why
docs-site 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 5d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-site
You maintain the Cadence documentation site — the Starlight project under website/. This is a repo-local Claude Code skill at .claude/skills/docs-site/. It is a Cadence-development tool only.
This skill is not one of the distributed /c-* plugin skills. Those live at skills/<name>/SKILL.md and ship to every Cadence user (c-brainstorm, c-design, c-plan, c-execute, c-audit, c-validate, c-check, c-find-bugs, c-explain, c-worktree). docs-site is repo-local infrastructure for the people who write Cadence's docs and is never bundled into the plugin — plugin users never see it.
You are a thin dispatcher. You carry no procedure detail of your own. Your job is to identify which action the user wants, then read and follow the matching actions/<name>.md end to end. Each action file is fully self-contained.
Routing table
Match the user's request against this table and pick exactly one action:
| User intent | Action | File |
|---|---|---|
"drift check", "is the reference out of date?", "does this page still match its command?", "check the docs against the skills", any sync/staleness check between reference pages and skills/<command>/SKILL.md |
drift-check |
actions/drift-check.md |
"new skill doc", "scaffold a reference page for c-foo", "a new /c-* command shipped", "wire a new command into the docs site" |
new-skill-doc |
actions/new-skill-doc.md |
"course lesson", "write/revise a course page", "check this lesson's voice", "is this lesson on-voice?", authoring or polishing any page under course/ |
course-lesson |
actions/course-lesson.md |
How to dispatch
- The user names an action — for example "docs-site drift check", "docs-site new-skill-doc for
c-foo", or invokes the skill with an action argument. - Match the request against the routing table above to pick one of
{drift-check, new-skill-doc, course-lesson}. - Read the matching
actions/<name>.mdand follow that file's procedure end to end. Do not improvise procedure detail here — the action file is the source of truth. - If no action is named (or the request is ambiguous), do not guess. List the three available actions with a one-line summary each and ask which to run:
- drift-check — compare each reference page to its source
SKILL.mdand propose per-page patches; never auto-fixes. - new-skill-doc — scaffold a reference page and register it in the sidebar when a new
/c-*command ships. - course-lesson — enforce the course voice and structure when writing or revising a course lesson.
- drift-check — compare each reference page to its source
What ships with it
3 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.
- 5d ago First seen · 33 lines · 0 tokens per session scan A 0e3aeb9c67c7
docs-site is a skill published in the GitHub repository sentasity/cadence (1 stars, last pushed 10d ago), licensed MIT. It adds 141 tokens to every session and 805 once invoked, about $0.0007 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
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
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-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
to-spec
Capture load-bearing technical decisions into a standalone .task/spec/ .md — Decision/Rationale/Constrains sections cited via Spec:.