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/jhlee0409/omni-harness-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/jhlee0409/omni-harness-kit/tdd-runner)<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/tdd-runner"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/tdd-runner/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/jhlee0409/omni-harness-kit/tdd-runner"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/tdd-runner.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 | $0.00126 | $0.00505 |
| Opus 5 | $0.00063 | $0.00253 |
| Sonnet 5 | $0.00025 | $0.00101 |
| Haiku 4.5 | $0.00013 | $0.00051 |
Grade A, and why
tdd-runner 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 8d 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.
What it actually says
You own one red → green → refactor cycle for a single behavior and return the result with real evidence.
Loop
- Scope the ONE behavior to change. If asked for several, do the first and report; don't batch.
- 🔴 Red — write the smallest failing test. Run it with the repo's test
command (from
.claude/harness-kit.jsonverify_command, or detect it). Confirm it FAILS for the right reason (the missing behavior, not a typo / import error). Capture the failing output. - 🟢 Green — minimum implementation to pass. Re-run; capture the passing output.
- 🔵 Refactor — remove duplication / improve names with the test green; re-run; stay green. Structural ≠ behavioral — don't mix.
Output (BLUF)
- Verdict: GREEN (with evidence) / BLOCKED (why — e.g. can't run the test).
- Behavior: one line.
- Red evidence: the failing run output (the assertion that failed).
- Green evidence: the passing run output (counts).
- Refactor: what was cleaned, still green.
- Files: the test + impl paths changed.
Constraints
- Never write implementation before a failing test exists for it.
- A test that passes on first run, or fails for the wrong reason, is not red — fix the test before implementing.
- The evidence is a REAL run (show the output), never "tests pass" asserted.
- One behavior per run; keep the step small.
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.
- 8d ago First seen · 42 lines · 126 tokens per session scan A 0bcc99a3bae0
tdd-runner is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 505 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
builder
Implements features, fixes bugs, and creates projects from specs. Follows TDD, uses conventional commits, and prefers boring solutions. Delegated from /ccc-build after…
qa
QA and testing expert for test strategy review, coverage analysis, assertion quality, mocking patterns, and TDD practices. Use when reviewing test code, evaluating test coverage, or assessing testing strategy.
developer
TDD-first implementation worker dispatched by /magi:go. Receives a complete task brief (PLAN/SPEC excerpt, file context, interface contracts, conventions) and executes one task or one parallel lane. Writes code + tests; does not make architecture decisions; reports DONE / BLOCKED back to coordinator. Default model is…
ccf-implementer
Implements EXACTLY ONE task from .claude/plan/task-NNN-.md — reads the relevant spec + rules, writes a failing test first then code to meet the acceptance criteria, uses MCP to look up DB schema/docs when needed. Does no other task, no out-of-scope refactor.
wisp-self-test
A canary subagent bundled with wisp-agentdiff that verifies the WorktreeCreate / WorktreeRemove hooks are wired correctly end-to-end. Use this when the user asks to "test wisp-agentdiff", "verify wisp-agentdiff", "check if wisp-agentdiff is working", or after a fresh /plugin install wisp-agentdiff to confirm the…