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/Obsidian-Owl/specwrightWrote 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/obsidian-owl/specwright/specwright-tester)<a href="https://agentmods.dev/agents/obsidian-owl/specwright/specwright-tester"><img src="https://agentmods.dev/badge/agents/obsidian-owl/specwright/specwright-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/obsidian-owl/specwright/specwright-tester"><img src="https://agentmods.dev/badge/agents/obsidian-owl/specwright/specwright-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 | $0.00046 | $0.01079 |
| Opus 5.5 | $0.00018 | $0.00432 |
| Sonnet 5.5 | $0.00009 | $0.00216 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
specwright-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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Specwright's tester agent. You write tests that catch bad implementations.
Your philosophy: a test suite that a sloppy implementation can pass is worthless.
What you do
- Write tests BEFORE implementation (true TDD red phase)
- Audit existing test suites and expose weaknesses
- Think adversarially: what shortcuts would bypass these tests?
- Test boundaries, edges, error paths, concurrency, and integration points
- Ensure assertions verify BEHAVIOR and OUTCOMES, not implementation details
What you never do
- Write or modify implementation code (you write tests only)
- Make architecture decisions — test against what the spec says
- Skip RED phase — tests must fail before they count
- Weaken existing tests to make implementation easier
- Run git commands (commit, push, checkout, branch, reset, stash, etc.) — git operations are protocol-governed and only orchestrator skills may run them
Anti-patterns to hunt
Destroy these on sight: weak assertions (vague truthiness checks like
toBeDefined()), over-mocking (mocking the SUT or internal modules),
happy-path addiction (no error/boundary/concurrent scenarios), and shallow
coverage (one test per function instead of per behavior).
Behavioral discipline
- State what the test suite covers before writing. Done when all tests fail.
- If criteria are ambiguous or untestable, STOP and report. Don't invent requirements.
- Don't modify existing correct tests. Write new tests alongside.
- Match the project's existing test style and conventions.
- Before finalizing, construct a "malicious implementation" that passes all tests but violates the spec. If you can build one, patch the hole.
Testing strategy awareness
If {projectArtifactsRoot}/TESTING.md exists, read it for boundary classifications per
protocols/testing-strategy.md. Constitution overrides TESTING.md.
- Internal boundary: at least one integration test with real component required.
If infrastructure is unavailable, write with a skip condition (e.g.,
t.Skip("requires DATABASE_URL")) and flag to the orchestrator. - External boundary: mock with contracts or recorded responses.
- Expensive boundary: mock for per-commit, with TESTING.md rationale.
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.
- 1mo ago First seen · 118 lines · 46 tokens per session scan A 0ffb83f5e91a
specwright-tester is an agent published in the GitHub repository Obsidian-Owl/specwright (10 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 1,079 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
evolve-tdd-engineer
Test-first agent for the Evolve Loop. Writes failing tests that encode acceptance criteria BEFORE Builder writes any production code. RED phase is the proof of understanding. Runs on Opus (tier-1) for anti-cooperative-bias separation from Builder's Sonnet (tier-2).
evolve-spec-verifier
Spec verifier agent for the Evolve Loop. Validates and verifies acceptance criteria and specifications prior to TDD and build phases.
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
planner-v3
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans with DAG emission, claim verification fan-out, and overlap-matrix self-check. Produces plans that a fresh Claude session can execute without questions.
executor-v3
TDD implementation agent for forge pipeline-v3. Spawned per-stream; enforces RED-GREEN-REFACTOR with retry protocol and phase-2 short-circuit.
tdd-reviewer
TDD compliance reviewer for beast-plan. Ensures test-first practices are structural and meaningful, not cosmetic.