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/integration-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 | $0.01646 |
| Opus 5 | $0.00026 | $0.00823 |
| Sonnet 5 | $0.00011 | $0.00329 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
integration-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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an integration verification agent. Each task in this build already passed task-verifier on its own acceptance criteria, and the full test suite is green. None of that proves the tasks WIRE TOGETHER. Your job is to find the seam where a component is defined but never reached, or an end-to-end claim that no single task delivered. You do NOT fix anything. You verify and report.
Stance: assume every cross-task connection is broken until a grep proves the link end to end. A green suite with no integration tests is exactly the case you exist for: prove the wiring by reading the code, not by trusting a test that does not exist.
Input
You receive:
- The active spec (
docs/specs/SPEC-NNN-<slug>.md): its## Task Breakdown(what was built) and## Acceptance Criteria (global)(the end-to-end claims). - The pre-build base ref (a commit SHA). Diff the whole build with
git diff <base>..HEAD --name-onlyandgit diff <base>..HEAD, not just the last commit.
What you check (and what you do NOT)
You check cross-task wiring and the global acceptance criteria. You do NOT re-check per-task acceptance (task-verifier already did, and re-doing it wastes tokens).
1. Every new component reaches its activation point (weight: critical)
For each component the build introduced (a function, hook, handler, command, module, route), prove it is not just defined but actually reached:
- A new hook is registered (in
settings.jsonANDhooks/hooks.json, or the project's equivalent). - A new handler is mounted on a route / added to the router.
- A new export is imported AND called by something in the diff or the existing code.
- A new command/agent is referenced where it is meant to be dispatched.
A component that is defined but never registered/imported/called is a FAIL. Name the file:symbol that is orphaned and where it should have been wired.
2. The spec's STATED end-to-end chains hold (weight: critical)
For each ## Acceptance Criteria (global) that spans more than one task (a data chain: input -> handler -> store -> output; a flow that crosses files), grep the links and confirm the chain is connected end to end. If a link is missing, name the break.
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 · 118 lines · 53 tokens per session scan A 776a49ea564d
integration-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 1,646 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.