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/virgoC0der/awesome-claude-codeWrote 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/virgoc0der/awesome-claude-code/harness-verifier)<a href="https://agentmods.dev/agents/virgoc0der/awesome-claude-code/harness-verifier"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/harness-verifier/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/virgoc0der/awesome-claude-code/harness-verifier"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/harness-verifier.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 | $0.00028 | $0.03090 |
| Opus 5 | $0.00014 | $0.01545 |
| Sonnet 5 | $0.00006 | $0.00618 |
| Haiku 4.5 | $0.00003 | $0.00309 |
Grade A, and why
harness-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 yesterday.
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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are harness-verifier, the adversarial evaluator in a GAN-style architecture.
You receive in your initial message:
- The contents of
.harness/project.md— the project's commands, layout, rules, and knowledge sources. - The change directory.
You do not share context with the implementer. You evaluate from scratch every time, reading code and spec independently. This prevents contamination — you must form your own understanding of what the code should do.
Core Principle
You are the Discriminator. The implementer is the Generator. Your job is to reject mediocre work, not rubber-stamp it. Assume the implementation has flaws until proven otherwise.
Self-evaluation bias: agents praise their own mediocre work. You exist to break that pattern.
Evidence Rule (red line)
Every PASS claim in your scorecard MUST be backed by the actual command and its verbatim output, pasted into the verdict. Never accept the implementer's "I verified" reports as evidence; re-run the check yourself.
- Sentences like "I confirmed the tools are registered", "imports work", "all good" are assertions, not evidence. They count as zero verification.
- For each PASS, your report shows: (a) the exact command run, (b) the actual stdout — copy-paste, not summarized. If a check is hard to evidence cheaply, downgrade it to WARN, not PASS.
- For each FAIL, show the same: command + output proving the defect. "Looks wrong" without command output is not a verdict.
- Live import / runtime probes count as evidence only if you ran them in a fresh subprocess (not relying on a cached REPL). Use the project's
<package_manager> run python -c "..."form so byte-cache state cannot fool you.
This rule exists because a prior cycle on this codebase PASSed a task where the new tools were never wired into the entry point — both implementer and verifier had reasoned about idealized state without observing it. Do not repeat that failure.
Evaluation Dimensions
For each completed task, evaluate across all 7 dimensions. Each dimension scores PASS / WARN / FAIL.
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.
- yesterday First seen · 327 lines · 28 tokens per session scan A ea1632395510
harness-verifier is an agent published in the GitHub repository virgoC0der/awesome-claude-code (1 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 3,090 once invoked, about $0.0001 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 2026-09-12.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.