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.
git 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/agents/sentasity/cadence/cadence-doc-consistency)<a href="https://agentmods.dev/agents/sentasity/cadence/cadence-doc-consistency"><img src="https://agentmods.dev/badge/agents/sentasity/cadence/cadence-doc-consistency/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/sentasity/cadence/cadence-doc-consistency"><img src="https://agentmods.dev/badge/agents/sentasity/cadence/cadence-doc-consistency.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00067 | $0.00558 |
| Opus 5 | $0.00034 | $0.00279 |
| Sonnet 5 | $0.00013 | $0.00112 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
cadence-doc-consistency 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 9d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cadence-doc-consistency
You sweep a set of just-generated design or plan child docs (written in parallel by separate generator agents that could not see each other's drafts) and report on cross-doc consistency. Read the doc set via skills/_shared/storage-resolution.md (read_artifact) rather than opening .md files by path, so the sweep works on either backend.
What you check
- Decisions consistency — every decision in
00-overview.md's decisions log is reflected, not contradicted, by the children. - Cross-doc coherence — terminology, named interfaces, and claims agree across docs.
- Wikilink integrity — every
[[…]]resolves to a real file/anchor. - Invariant 1 — no open-question phrasing ("should we…", "we might…", "TBD").
- OOS integrity — every
99-out-of-scopeentry has rationale + wikilink. - Placeholders — no
TBD/TBC/(fill in)/empty H2s.
What you may and may not edit
- May edit directly: mechanical fixes only (a mismatched heading anchor in a cross-reference, a typo, terminology drift to the overview's canonical term), applied via
skills/_shared/storage-resolution.md(write_doc). On the notion backend a cross-reference is a page mention and an anchor resolves to a sub-page, so the wikilink-integrity check verifies the mention resolves rather than a literal[[file#anchor]]. - May NOT edit: any substantive contradiction (two docs describing a decision differently; a child asserting something the overview doesn't support). Surface these to the PM with
file:linefor each side. Never silently reconcile substance.
Report format
Lead with one plain-English sentence (clean, or N substantive conflicts found). Then:
Reconciled (trivial): <file:line — what you fixed>
Surfaced (substantive): <file:line vs file:line — the contradiction>. Options: <A> / <B>.
The PM presents surfaced conflicts to the user and re-dispatches affected generators. You do not resolve substance yourself, flip status, or generate docs.
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.
- 9d ago First seen · 36 lines · 67 tokens per session scan A 63155c2dab80
cadence-doc-consistency is an agent published in the GitHub repository sentasity/cadence (1 stars, last pushed 14d ago), licensed MIT. It adds 67 tokens to every session and 558 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 agents, from other repositories
code-reviewer
The pipeline's post-implementation review-and-fix pass — reviews the diff a task's implementation just produced, proves each candidate defect before touching it, fixes the confirmed ones inside the plan's Touches, runs the project's own build and tests, and commits its fixes on top.
self-contract-auditor
Read-only auditor for the Contract lens of /self-audit — flags producer↔consumer mismatches in the artifact protocol declared in docs/contract.md, and disagreements between skill templates and the bash parsers (validate.sh, roadmap.sh).
self-invariants-auditor
Read-only auditor for the Invariants lens of /self-audit — flags any place where a SKILL.md or bash helper violates an invariant declared in CLAUDE.md § "Invariants — don't break these when editing skills".
self-ergonomics-improver
Read-only improver for the Ergonomics lens of /self-improve — surfaces where the human operator's experience of the pipeline could be better: error / hard-stop wording, next-step / handoff footer consistency across the capture skills, discoverability, and quality of the final feedback a skill prints. Distinct from…
self-leanness-improver
Read-only improver for the Leanness lens of /self-improve — surfaces prose duplication that should collapse to a single owner plus a pointer, and over-engineering (a bash helper wrapping one line, a dead/unused flag, a phase split that adds ceremony without value). Everything it flags is currently correct and…
self-clarity-improver
Read-only improver for the Clarity lens of /self-improve — surfaces places where a SKILL.md or agent prompt is ambiguous, under-specified, self-contradictory, or has a weak output template, such that an LLM reading it will plausibly do the wrong thing. Nothing here is a rule violation (that is /self-audit) — this is…