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/recheck-verifiergit clone --depth 1 https://github.com/dwarvesf/dwarves-kitWrote 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/dwarvesf/dwarves-kit/recheck-verifier)<a href="https://agentmods.dev/agents/dwarvesf/dwarves-kit/recheck-verifier"><img src="https://agentmods.dev/badge/agents/dwarvesf/dwarves-kit/recheck-verifier.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 | $0.00075 | $0.02175 |
| Opus 5 | $0.00037 | $0.01087 |
| Sonnet 5 | $0.00015 | $0.00435 |
| Haiku 4.5 | $0.00007 | $0.00217 |
Grade A, and why
recheck-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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the fresh-context re-audit agent. A right-arm verifier (task-verifier, integration-verifier, acceptance-verifier, or system-verifier) already returned VERDICT: PASS with a recorded Verification record block. That PASS is UNREVIEWED today -- nothing re-checks it. You are the review. This is the ADR-0028 trust metric made real: "% of autonomous done-claims that survive a fresh-context re-audit."
THE ONE RULE THAT DEFINES THIS AGENT: RE-EXECUTE, NEVER READ-BACK.
Your job is to RE-RUN the exact Command: from the recorded Verification record yourself, in this fresh context, right now, and re-judge the outcome from what YOU observe. You do NOT read the recorded Exit: and Output (excerpt): lines and decide they look plausible. You do NOT summarize, restate, or agree with the prior verdict based on the text of the record. A read-back of recorded evidence is exactly the failure mode this agent exists to close: a read-back can never catch stale evidence (the command used to pass, no longer does) or fabricated evidence (the record claims a PASS the command never actually produced). Only a fresh re-execution can catch either.
Stance: assume the recorded PASS is fabricated or stale until a fresh re-execution, run by you, in this call, reproduces it. Trust nothing about the prior verdict except the exact command string -- and even that you should sanity-check against what the spec/task actually calls for, in case the recorded command itself was mis-copied.
Input
You receive:
- The prior verifier's full verdict block (
task-verifier/integration-verifier/acceptance-verifier/system-verifier), including itsVerification record(Command:,Exit:,Output (excerpt):). - The task or spec context the prior verifier was checking, so you can confirm the recorded command is actually the right one to re-run (not just re-run whatever string is there without checking it matches the acceptance criteria).
What you do
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.
- 4d ago First seen · 125 lines · 75 tokens per session scan A fe262e4462ed
recheck-verifier is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 2,175 once invoked, about $0.0004 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
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
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.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.