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/attilaszasz/sdd-pilotWrote 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/attilaszasz/sdd-pilot/sddp-test-evaluator)<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/sddp-test-evaluator"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/sddp-test-evaluator/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/attilaszasz/sdd-pilot/sddp-test-evaluator"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/sddp-test-evaluator.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 | $0.00029 | $0.00067 |
| Opus 5 | $0.00015 | $0.00034 |
| Sonnet 5 | $0.00006 | $0.00013 |
| Haiku 4.5 | $0.00003 | $0.00007 |
Grade A, and why
sddp-test-evaluator 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.
What it actually says
Read and follow the methodology in .github/agents/_test-evaluator.md.
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 · 8 lines · 29 tokens per session scan A f52ff04cff9e
sddp-test-evaluator is an agent published in the GitHub repository attilaszasz/sdd-pilot (96 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 67 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 2026-08-30.
Other agents, from other repositories
task-verifier
Verifies a completed task against its spec acceptance criteria. Run after each worker subagent completes a task. Read-only -- cannot modify the codebase.
break-it
The adversarial prober lens. Given a branch whose behavioral code carries a green test suite, it hunts for a concrete INPUT or CALL SEQUENCE the suite does not constrain -- one that changes behavior without failing any test. Escalation-tier lens dispatched from /kit:battery when the diff carries behavioral code with…
recheck-verifier
Fresh-context re-audit of a right-arm verifier's PASS (task-verifier / integration-verifier / acceptance-verifier / system-verifier). RE-EXECUTES the recorded verification command in a fresh context and re-judges the outcome; it is NOT a read-back of the recorded run-table. Read-only -- cannot modify the codebase.
acceptance-verifier
Dynamically executes the active spec's acceptance criteria via its ## Verification section and reports whether the build actually satisfies them. Fills the agent-less Acceptance row of the V-model right arm. Read-only -- cannot modify the codebase.
angular-test-engineer
Phase 4 (red step) — write the failing frontend test for each Angular task before any production code. Use when running /build for frontend tasks.
spring-implementer
Phase 4 (green/refactor/simplify) — minimum production code to pass the failing test, then refactor without behavior change, then apply clarity-over-cleverness.