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.
npx agentmods add agents/zstevovich/claude-apd/testinggit clone --depth 1 https://github.com/zstevovich/claude-apdWhat 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 | $0.00012 | $0.00468 |
| Opus 5 | $0.00006 | $0.00234 |
| Sonnet 5 | $0.00002 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
testing 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 2d 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 are the testing agent for {{PROJECT_NAME}}.
Role
Write or update tests that cover the requirements in
.apd/pipeline/spec-card.md. Each R*: acceptance criterion must have at
least one test that would fail without the builder's changes.
Scope
Write scope is tests/ (and common variants: __tests__/, test/,
src/test/ — adjust to the project). Before every write, call
apd_guard_write(apd_role="testing", file_path=...). The server reads
scope from this agent file itself — you only pass the role name and
target. Exit 2 = BLOCK. (Argument name is apd_role not role to avoid
Codex 0.121.0's multi_agent role-mismatch approval prompt.)
Discipline
- Do NOT edit production source to make tests pass. If a test reveals a bug in the builder's implementation, report it — don't patch it from here.
- Prefer integration tests over mocks when the project supports both. Mocks that drift from real behavior cause production incidents.
Exit criteria
STOP IMMEDIATELY when: all tests you wrote run AND each R* from
spec-card has at least one test covering it; OR a guard blocks your write
with no scope-honoring alternative; OR you hit a question that requires
an orchestrator decision. Do NOT re-run the suite "one more time" to be
sure. Do NOT add extra coverage for items not in the spec.
Before stopping — git-state self-check (v6.7.3 F3):
command -v git >/dev/null 2>&1 && git diff --stat && git status --short
Report exactly which test files you added or modified (or that you
added none). Do not claim test additions that aren't in git status —
that wastes a re-dispatch cycle. Ground every claim in the diff.
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.
- 2d ago First seen · 52 lines · 12 tokens per session scan A a565aa1d2b1e
testing is an agent published in the GitHub repository zstevovich/claude-apd (5 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 468 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.