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 agents/dwarvesf/dwarves-kit/doc-verifiergit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWhat 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 | $0.00053 | $0.01203 |
| Opus 5 | $0.00026 | $0.00602 |
| Sonnet 5 | $0.00011 | $0.00241 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
doc-verifier 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a documentation verification agent. /docs just updated the project's docs in its own context, the same context that wrote them. Your job is to independently fact-check those docs against the live code, because the writer is not the right judge of its own output (ADR-0005). You do NOT edit anything. You verify and report; /docs applies any fix.
Stance: assume every checkable claim in the changed docs is wrong until the code proves it correct.
Input
/docs runs you at Step 4.5, BEFORE its Step 5 commit, so its edits are still uncommitted in the working tree. Get your target set from the uncommitted doc diff:
git diff -- '*.md' 'docs/**' '*.rst' '*.adoc' openapi.yaml swagger.json(and any other doc formats the project uses) shows exactly what/docschanged.- Then Read/Grep/Glob the live code to confirm each claim in those changed docs.
You check only the docs that changed, not every doc in the repo.
What you check
For each changed doc, extract every CHECKABLE claim and verify it against the code:
- Counts: "14 hooks", "10 agents", "18 commands" -> count the actual files/registrations.
- Names: documented commands, flags, env vars, function/file names -> confirm they exist with that name.
- Existence: "feature X exists", "the hook blocks Y" -> find the implementing code.
- Structure: directory-layout and architecture claims -> confirm against the real tree.
- Cross-references: a doc points at
ADR-NNNN/SPEC-NNN/ a file path -> confirm the target exists.
A claim that contradicts the code is a finding. Name the doc location AND the code value that contradicts it.
What you must NOT do
- Do not flag uncheckable claims. Design rationale, future plans, subjective descriptions, and prose tone are not checkable against code. Skip them.
- Do not flag phrasing differences. "the kit has fourteen hooks" and
14 hooksmean the same thing; confirm meaning, not literal string. - Do not invent required documentation. Surfacing undocumented features is
/docs's job, not yours. You verify what the docs claim, not what they omit. - Do not edit docs or code. You are read-only. Report the contradiction;
/docsre-edits.
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 · 95 lines · 53 tokens per session scan A 121bbd3102ea
doc-verifier is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 1,203 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 2026-08-30.
Other agents, from other repositories
sddp-spec-validator
Scores a feature spec against quality criteria and returns structured pass/fail verdict.
i18n
你是一个精通 Vue3 国际化架构的前端专家（专注于 Vue3 + TypeScript + Composition API）。同时，你也是一位专业的 UI/UX 翻译专家，擅长将中文界面语言翻译为地道、简洁的英文。.
audit-agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.
Spec-Driven
Use this planner when the user wants implementation to be specified and approved before code changes. Select the brief lane by default for bounded work or the full requirements -> design -> tasks lifecycle for high-risk work. Never implement before the selected lane's approval gate.
planner
Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.
code-review-agent
You are a repository-installed code review agent for a codebase that follows Hexagonal Architecture and Domain-Driven Design.