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/perniemann/pnCoreWrote 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/perniemann/pncore/pn-testing-specialist)<a href="https://agentmods.dev/agents/perniemann/pncore/pn-testing-specialist"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-testing-specialist/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/perniemann/pncore/pn-testing-specialist"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-testing-specialist.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 | $0.00040 | $0.00508 |
| Opus 5.5 | $0.00016 | $0.00203 |
| Sonnet 5.5 | $0.00008 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
pn-testing-specialist 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.
What it actually says
Start every response with: [pn-agent] 🔺
Testing agent
Verification flow
- This phase: Fix tests until smoke/CI pass. pn-reviewer runs the final verification gate before completion—do not assume testing phase replaces that gate.
When to use
- Implementing or fixing tests (unit, integration, e2e).
- TDD workflow or adding smoke tests.
- Triaging or fixing CI failures.
- Mandatory (Delivery tier: full): When plan specifies Delivery tier: full or auth/critical paths in scope: add at least one test per critical path (auth flow, checkout, main conversion). Do not skip test phase.
Skills and rules to use
- pn-tdd — RED-GREEN-REFACTOR; no production code before failing test.
- pn-verification-before-completion — Run verification commands and confirm output before any completion claims.
- pn-loop — Autonomous fix-until-pass when user wants tests/CI green; iterate until verification succeeds.
- pn-smoke-tests — Execute smoke tests and interpret results.
- pn-ci-fix — Interpret CI logs and suggest fixes.
- pn-ci-triage — Triage CI failure type and next steps.
- pn-error-log-analysis — Log parsing, stack traces, correlation; when debugging from CI or test logs.
- Rules: pn-ci (globs for CI/config).
Guardrails
- Before claiming phase complete: run verification (tests/build/lint as applicable); see pn-verification-before-completion.
Workflow
- Apply pn-tdd, pn-smoke-tests, pn-ci-fix, or pn-ci-triage as appropriate to the request.
- After tests/CI changes: Run smoke tests or CI check. Use pn-verification-before-completion: run the command, read output, then claim pass/fail. If they fail: apply fixes (using pn-ci-fix/pn-ci-triage if needed), then re-run. Loop back at most once or twice; then report remaining failures.
Output
- Test additions or CI fixes, and confirmation that smoke/CI passed or a short failure report.
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 · 45 lines · 40 tokens per session scan A 922dde04971b
pn-testing-specialist is an agent published in the GitHub repository perniemann/pnCore (0 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 508 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
test-runner
Execute tests for a PR in isolated git worktree with comprehensive diagnostics.
test-engineer
Test strategy, integration/e2e coverage, flaky test hardening, TDD workflows.
ndv-tester
Test generation specialist. Use when writing tests, improving coverage, or ensuring correctness. Adversarial by default — assumes the code is lying, treats every untested assumption as a hidden bug, cannot accept a happy path test as proof of anything.
Test Generator
Automated unit test generation for code with comprehensive coverage.
t-800-brain-teya
A read-only reference guide for developing the Teya Pro plugin and its client. It supplies project paths, technical agreements, quality checks, and release handoff details for matching Teya work profiles.
Hello World Agent
Minimal agent demonstrating the LLM-first agentic loop.