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/ecro/harness-maker/test-researchgit clone --depth 1 https://github.com/Ecro/harness-makerWhat 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 | $0.00000 | $0.00366 |
| Opus 5 | $0.00000 | $0.00183 |
| Sonnet 5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
test-research 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
/hm:test-research
harness-maker Phase 1 fixture for verifying that slash commands and Q&A loops work in both IDEs.
Mission
Follow this procedure exactly.
Step 1 — Ask the user
Ask the user the following question:
"Phase 1 A4 verification — Which IDE / mode is running this command?
- Claude Code
- Cursor (Plan Mode, entered via Shift+Tab)
- Cursor (Agent Mode, default)
- Other (free-text)"
Question-tool selection:
- Claude Code — use
AskUserQuestion(structured 4-option select) - Cursor Plan Mode — Cursor's native AskQuestion tool fires automatically
- Cursor Agent Mode — fall back to natural-language chat (PASS if it works equivalently)
Step 2 — Output a single line
Once the answer is in, output exactly:
PHASE-1 A4 PASSED — slash command + Q&A loop works in <user answer>
Step 3 — Stop
No additional work. No analysis. No further tool calls.
Verification points
- Command discovery: when the user types
/hm:test-research, the IDE shows it in the slash-command dropdown - Q&A loop: an interview-style question receives a user response and the command flow continues
- Natural-language fallback: if structured Q&A tools are unavailable, plain chat works equivalently
Note
This fixture lives at .claude/commands/hm/. If Cursor does not recognize this location (i.e. command does not appear in the dropdown), a separate render to .cursor/commands/ will be required (Phase 2 design decision).
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 · 46 lines · 0 tokens per session scan A f141192b69a6
test-research is a command published in the GitHub repository Ecro/harness-maker (4 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 366 tokens. 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
constitution
根据交互输入或已提供原则创建或更新项目章程，并确保相关模板保持同步。.
meta-theory-verify
Run the appropriate MetaKim verification path.
cross-research
Two-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via fresh Claude session. Usage: /cross-research [--with | list | compare].
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name].