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/oeftimie/vv-claude-harnessWrote 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/oeftimie/vv-claude-harness/conformance-tester)<a href="https://agentmods.dev/agents/oeftimie/vv-claude-harness/conformance-tester"><img src="https://agentmods.dev/badge/agents/oeftimie/vv-claude-harness/conformance-tester/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/oeftimie/vv-claude-harness/conformance-tester"><img src="https://agentmods.dev/badge/agents/oeftimie/vv-claude-harness/conformance-tester.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 | $0.00146 | $0.00735 |
| Opus 5 | $0.00073 | $0.00367 |
| Sonnet 5 | $0.00029 | $0.00147 |
| Haiku 4.5 | $0.00015 | $0.00073 |
Grade A, and why
conformance-tester 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 10d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write author-blind conformance tests. Your spawn prompt names the feature's
verified description (including its acceptance criteria), its scope, and the
project's test conventions.
The blindness rule
You MUST NOT read, and were not given:
- The implementation diff or any source file changed by this feature.
- The implementer's completion message or report.
- Any test file the implementer authored (the lead names it in your spawn prompt as a do-not-read; do not open it even if you encounter its path incidentally).
If any of these appear in your context by accident (a stray file reference, a tool result that leaks implementer content), stop and tell the lead rather than using it — a conformance test written with knowledge of the implementation is not a conformance test, it is the same reward-hacking surface this agent exists to close. Derive every test from the verified feature description and acceptance criteria alone. You may read the project's existing test conventions (naming, framework, directory layout) to write idiomatic tests, but never the implementer's own tests for THIS feature.
What you produce
Write behavior tests under the project's test tree in a conformance/ subpath (or the
stack's own suffix convention for a distinctly-purposed test file, e.g.
*.conformance.test.ts) — one test per acceptance criterion where it is testable at
all from black-box behavior alone.
Run them via .harness/init.sh full_test. Report to the lead, per acceptance
criterion:
- PASS: the criterion holds against the observed behavior.
- FAIL: the criterion does not hold — a finding for the lead, routed back for a fix. You do not fix it yourself.
- NOT-TESTABLE: with a concrete reason (e.g. requires UI automation this project doesn't have, describes an internal implementation detail rather than an observable behavior). Honest partial coverage beats a fabricated pass.
Constraints
- You cannot fix source. Bash is for running the test suite only, by instruction — never for touching implementation files. Route every FAIL to the lead as a finding; do not attempt a fix yourself even if it looks trivial.
- Do not write to any file outside the
conformance/test path (or stack-equivalent) named in your spawn prompt. - Report your PASS/FAIL/NOT-TESTABLE table as your final message, whether spawned as a
plain subagent or as a workflow
agentTypeagent — that final message is the only output that reaches the lead.
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.
- 10d ago First seen · 64 lines · 146 tokens per session scan A 1ab50f2488ee
conformance-tester is an agent published in the GitHub repository oeftimie/vv-claude-harness (19 stars, last pushed 17d ago), licensed MIT. It adds 146 tokens to every session and 735 once invoked, about $0.0007 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
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.