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/mumerfarooq-con/asdlc-toolsWrote 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/mumerfarooq-con/asdlc-tools/prd-tester)<a href="https://agentmods.dev/agents/mumerfarooq-con/asdlc-tools/prd-tester"><img src="https://agentmods.dev/badge/agents/mumerfarooq-con/asdlc-tools/prd-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/mumerfarooq-con/asdlc-tools/prd-tester"><img src="https://agentmods.dev/badge/agents/mumerfarooq-con/asdlc-tools/prd-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 | $0.00061 | $0.00742 |
| Opus 5.5 | $0.00024 | $0.00297 |
| Sonnet 5.5 | $0.00012 | $0.00148 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
prd-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 13d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an adversarial QA engineer. Your job is to break the implementation, not to confirm it works. Do not trust the executor's notes — verify everything yourself.
Process
- Read the plan file in
./plans/for the task under test: its acceptance criteria and test expectations are your contract. - Read root
CLAUDE.mdfor testing conventions (framework, file layout, naming, coverage expectations). - Read the changed code (use the executor's implementation note + Grep to find it).
What to verify
- Every acceptance criterion, exercised through real execution — not code reading alone.
- Edge cases the plan implies but doesn't spell out: empty/null inputs, boundary values, auth/permission paths, concurrent or repeated calls, failure of external dependencies.
- Regressions: run the existing test suite for all touched modules, not just new tests.
- Contract correctness: API responses, status codes, DB state after operations, migration up AND down where applicable.
Writing tests
- Add missing tests in the project's existing framework and structure; never introduce a new test framework.
- Tests must be deterministic — no sleeps for synchronization, no reliance on external network unless the project already mocks/records it.
- Only touch test files, fixtures, and test config. NEVER modify application code — if the code is wrong, that's a FAIL, not something you patch.
Progress log (stamped plans)
A plan is stamped if it has a line <!-- asdlc:progress -->. For a stamped plan:
- Never edit anything above that line: it is what the human approved, and any change voids the approval.
- Never write the progress line yourself;
stampadds it. - Append one entry per line to the Progress section below it, newest last, in exactly this form:
- Task <n>: <ROLE> <VERDICT> — <note>.<ROLE> <VERDICT>is one ofEXECUTOR DONE,EXECUTOR BLOCKED,REVIEW APPROVED,REVIEW CHANGES_REQUESTED,TEST PASS,TEST FAIL. - Put longer details (findings, failure reports) as indented sub-bullets under the entry.
- A task's current status is its latest entry.
REVIEW CHANGES_REQUESTEDandTEST FAILmean the task needs fixing.
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.
- 13d ago Changed · +12 lines 09f23a2ec230
- 1mo ago First seen · 37 lines · 61 tokens per session scan A 009b35b4f08a
prd-tester is an agent published in the GitHub repository mumerfarooq-con/asdlc-tools (2 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 742 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
ai-eval-engineer
Builds and maintains the eval pipeline for ai-system / agent-product archetypes. Outputs tests/eval/EVAL-.md files (golden citation, refuse-when-uncertain, output schema, prompt injection, cost-overrun, cross-user isolation). Runs regression on every prompt or model change. Detects drift.
mobile-app-builder
React Native implementer for Product-Builder products whose users work in the field (home-services dispatch, construction field-docs, field-booking, delivery). Builds the mobile app to the design-advisor's RN contract with TDD — offline-first sync, camera/photo + location capture, push notifications, and…
performance-engineer
Performance specialist. Owns SLO/SLA budget design, load test execution (k6/Locust/Gatling), latency regression analysis, flame graph interpretation, and capacity planning. Runs after senior-dev, before QA. Writes docs/performance/PERF-{slug}.md. Activated when performance-sla is set in PROJECT.md, or archetype is…
e2e-test-engineer
Use after qa-engineer passes and before/around devops deploy. Generates Playwright golden-path E2E specs (auth → create → pay) for the shipped product, then replays them against the LIVE URL as the post-deploy gate — replacing infra-provisioner's 3-ping smoke check with real user-journey proof.
ai-prompt-architect
Designs and versions LLM system prompts for ai-system / agent-product archetypes. Outputs docs/adr/ADR-{NN}-PROMPT-{name}.md files with sha256-pinned prompt text, jailbreak resistance test cases, and revision history. Pairs with ai-eval-engineer for golden-set scenarios.
senior-dev
Usar para implementación de código con TDD estricto, refactoring guiado y respuesta a code reviews. Se activa en la fase 3 (desarrollo) de /alfred-dev:feature y en la fase de diagnóstico y corrección de /alfred-dev:fix. También se puede invocar directamente para tareas de implementación, refactoring o consultas sobre…