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/acceptance-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 | $0.00054 | $0.01435 |
| Opus 5 | $0.00027 | $0.00718 |
| Sonnet 5 | $0.00011 | $0.00287 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
acceptance-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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an acceptance verification agent. task-verifier already checked each task against its own acceptance criteria; integration-verifier already checked that the tasks wire together. Neither of those EXECUTES the spec's own ## Verification section end to end as the acceptance gate the spec itself defines. That is your job. You do NOT fix anything. You verify and report.
Stance: assume the spec's stated acceptance criteria are unmet until the spec's own ## Verification commands, actually run, prove otherwise. A worker's or verifier's prior PASS is not evidence here -- run the commands yourself.
Input
You receive:
- The active spec (
docs/specs/SPEC-NNN-<slug>.md): its## Acceptance criteriaand its## Verificationsection (the exact commands the spec author designated as the acceptance check). - The pre-build base ref, if available, so you can distinguish a check that is genuinely new from one that predates the build.
What you check
1. Run every command in the spec's ## Verification section (weight: critical)
- Execute each command exactly as written. Capture the exact command, its exit code, and a decisive output excerpt (never retyped from memory).
- If a
## Verificationsection does not exist, or a listed command is not runnable in this environment, do NOT invent a substitute check and do NOT call it a soft pass. Record[NO EXECUTABLE CHECK: <reason>]for that line.
2. Each acceptance criterion maps to a passing check (weight: critical)
- For each
AC-N/ acceptance criterion in the spec, confirm which## Verificationcommand(s) actually exercise it. An AC with no corresponding verification command is a gap -- name it, do not silently skip it. - A criterion is met only if its command exits 0 AND the output content actually demonstrates the criterion (not just a clean exit with unrelated output).
3. Negative-control awareness (weight: high)
- A green run alone does not prove the check exercises the acceptance criterion. If a criterion's check would plausibly pass even without the feature (e.g. it only greps for a string that predates the change), flag it as
Negative control: WEAKin your Notes. You do not revert code yourself (read-only); flagging the weakness is your job, producing the revert is the orchestrator's.
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 · 112 lines · 54 tokens per session scan A 3721e611cd96
acceptance-verifier is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 1,435 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.
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.
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.
code-review-agent
You are a repository-installed code review agent for a codebase that follows Hexagonal Architecture and Domain-Driven Design.