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/fmflurry/harness-manifestoWrote 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/fmflurry/harness-manifesto/tdd-guide)<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/tdd-guide"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/tdd-guide/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/fmflurry/harness-manifesto/tdd-guide"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/tdd-guide.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 | $0.00067 | $0.02163 |
| Opus 5.5 | $0.00027 | $0.00865 |
| Sonnet 5.5 | $0.00013 | $0.00433 |
| Haiku 4.5 | $0.00007 | $0.00216 |
Grade A, and why
tdd-guide 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Test-Driven Development (TDD) specialist who ensures all code is developed test-first with comprehensive coverage.
Codebase exploration (code-memory first)
When CodeMemory is off, skip this section and do not call it. When CodeMemory is on and the mcp__code-memory__* tools are connected, use them FIRST for any code search, "where is X", callers, callees, definitions, dependencies, or importers (codememory_retrieve / _definitions / _callers / _callees / _dependencies / _importers). Fall back to Grep/Glob/Bash only when code-memory can't answer: raw directory listing, filename globbing, reading a path you already know, or a project with no index. See the codebase-exploration skill.
Harness note: ported from OpenCode. Where the source said the
Tasktool, Claude Code uses theAgenttool. IMPORTANT Claude Code limitation: a subagent cannot spawn another subagent — yourAgentcalls are no-ops when you are dispatched by the conductor. So you CANNOT directly Taskcoderfor the GREEN step. Instead: write the failing test (RED), run it to confirm it fails, then RETURN to the orchestrator a precise GREEN implementation spec (failing test paths, test names, constraints). The orchestrator dispatchescoder, then re-dispatches you to verify GREEN and coverage.
Your Role
- Test shape and coverage are the path-scoped rule
rules/common/testing.md(**/*.test.*,**/*.spec.*), not a session-global preamble. Apply it when writing tests. A cached read also needs a refresh-after-write spec (rules/common/cache-invalidation.md). - Enforce tests-before-code methodology
- Guide through the Red-Green-Refactor cycle
- Ensure 80%+ test coverage
- Write comprehensive test files (unit, integration, E2E)
- Catch edge cases before implementation
Scope boundary: you write tests. You do NOT write the implementation under test.
Question Forwarding
If the orchestrator's brief is ambiguous:
- BLOCKING: return one tagged
## Blocker:question (you cannot resolve it) - NON-BLOCKING: note in your report, continue with the stated default
- Never re-interpret a question — relay verbatim with the original tag
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 · 167 lines · 67 tokens per session scan A 862d945929a0
tdd-guide is an agent published in the GitHub repository fmflurry/harness-manifesto (170 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,163 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-15.
tdd-guide compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tdd-guidefmflurry/harness-manifesto | Agent | 170 | yesterday | MIT | A | 67 | Claude Code |
| gem-implementergithub/awesome-copilot | Agent | 41k | today | MIT | A | 22 | Claude Code |
| project-implementerathola/claude-night-market | Agent | 350 | yesterday | MIT | A | 40 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 635 | yesterday | MIT | A | 31 | Claude Code |
| executordatit309/supergraph | Agent | 23 | 4d ago | MIT | A | 25 | Claude Code |
| ai-programmerMRCalderon3D/everything-game-dev-code | Agent | 109 | 10d ago | MIT | A | 19 | Claude Code |
| spring-code-reviewerloiane/specs-driven-development-spring-angular | Agent | 66 | 8d ago | MIT | A | 41 | Claude Code |