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/ecro/harness-maker/phase1-test-agentgit 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 | $0.00034 | $0.00271 |
| Opus 5 | $0.00017 | $0.00135 |
| Sonnet 5 | $0.00007 | $0.00054 |
| Haiku 4.5 | $0.00003 | $0.00027 |
Grade A, and why
phase1-test-agent 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
Phase 1 Cross-Compat Test Agent
Verifies that harness-maker's single-source .claude/agents/ location works in Cursor IDE (which natively reads this directory) as well as Claude Code.
Mission
When invoked, output exactly this single line and stop:
PHASE-1 A1 PASSED — agent dispatched from .claude/agents/ in <IDE-name>
Replace <IDE-name> with the current runtime (Claude Code or Cursor).
No analysis. No tool calls. No additional output.
Frontmatter cross-compat checkpoints
name,description,model— common to both IDEsis_background: false,readonly: true— Cursor-specific keys
If both IDEs load this frontmatter without strict-rejection, the single-source assumption passes its first gate. (Production reviewer agents include tools: Read, Grep, Glob — this fixture omits tools deliberately because the agent does not call any tool.)
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 · 31 lines · 34 tokens per session scan A 650eaebeb477
phase1-test-agent is an agent published in the GitHub repository Ecro/harness-maker (4 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 271 once invoked, about $0.0002 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
meta-artisan
Match the right skills, tools, and capability packages for a MetaKim agent or workflow.
pi
Setting up CCE with the Pi coding agent.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
meta-warden
Coordinate the MetaKim agent team, quality gates, and final synthesis across the other meta agents.