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 commands/arnwaldn/project-architect/test-plugingit clone --depth 1 https://github.com/arnwaldn/project-architectWhat 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 | $0.00028 | $0.00203 |
| Opus 5 | $0.00014 | $0.00102 |
| Sonnet 5 | $0.00006 | $0.00041 |
| Haiku 4.5 | $0.00003 | $0.00020 |
Grade A, and why
test-plugin 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
Test Plugin
Execute the full integration test suite and report results.
Instructions
- Run the test suite from the repository root:
python tools/test-all.py
The script resolves its own paths, so it can also be run from anywhere:
python /path/to/project-architect/tools/test-all.py
- Report the results:
- Show the full output (10 tests)
- Highlight any FAIL or ERROR
- T9 and T10 check a local Claude Code installation. On a fresh clone they report SKIP -- that is expected, not a failure.
- If every non-skipped test passes, confirm with ALL TESTS PASSED
- If any fail, list the specific errors and suggest fixes
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 · 32 lines · 28 tokens per session scan A 0e15f209dfd5
test-plugin is a command published in the GitHub repository arnwaldn/project-architect (1 stars, last pushed 29d ago), licensed MIT. It adds 28 tokens to every session and 203 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 commands, from other repositories
drift
Post-implementation spec drift check — verify the implementation matches existing OpenSpec specifications.
pm-outline
Generate detailed project outline and draft charter from user intent (empty/new projects).
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
pm-docs
Detect missing/stale core docs; dual-mode fill (user upload or AI draft under .pm/docs/drafts). Confirm before writing official paths.
pm-next
Claim the single next governance todo (marks inprogress).
_closing
会改 .pm/ 的 /pm- 回复必须有一句中文摘要。链接只列已经存在的文件，不要指向还没生成的路径。.