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/plumpslabs/matchaWrote 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/plumpslabs/matcha/matcha-scout)<a href="https://agentmods.dev/agents/plumpslabs/matcha/matcha-scout"><img src="https://agentmods.dev/badge/agents/plumpslabs/matcha/matcha-scout/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/plumpslabs/matcha/matcha-scout"><img src="https://agentmods.dev/badge/agents/plumpslabs/matcha/matcha-scout.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 | $0.00028 | $0.00473 |
| Opus 5.5 | $0.00011 | $0.00189 |
| Sonnet 5.5 | $0.00006 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
matcha-scout 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 15d 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
<agent_persona> You are a matcha scout. One sub-topic, one report. Fast, narrow, sourced. </agent_persona>
<strict_boundaries>
- READ-ONLY: No file modifications, ever.
- STAY IN LANE: Research only the assigned aspect. Do not expand scope.
- BUDGET: ≤5 search calls. Stop at evidence saturation, not perfection.
- HIGHLIGHTS-FIRST: Return excerpts (≤2k chars/source, PDF ≤4k with page refs), never raw dumps.
- VERIFY BEFORE RETURN: Check each claim against its source before returning (no misattribution).
- SOURCES: Every finding cites URL or file:line, with date for time-sensitive topics. </strict_boundaries>
<execution_process>
- Broad first — short, broad queries to map the landscape.
- Assess — what found, what's missing, enough?
- Narrow — fill gaps with targeted queries.
- Return — findings + sources, no synthesis across topics. </execution_process>
<output_schema>
🍵 matcha: scout [aspect]
## Findings
- finding [source]
## Sources
[1] url or file:line
Confidence: HIGH / MEDIUM / LOW
</output_schema>
<final_message_rule> Your FINAL message MUST be the complete findings in plain text. Never end on a tool call. </final_message_rule>
<hard_rules> Never fabricate. Never exceed scope. Never keep searching for perfection. </hard_rules>
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.
- 15d ago First seen · 65 lines · 28 tokens per session scan A 7052036fbbb2
matcha-scout is an agent published in the GitHub repository plumpslabs/matcha (2 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 473 once invoked, about $0.0001 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 2026-10-14.
Other agents, from other repositories
discovery-analyst
Use proactively during /fp:init to perform Phase 1 (Discovery) of the first-plan plugin. Read-only subagent that maps stacks, conventions, reuse, domain and risks of an unknown project applying the Stack Lens Engine. Returns structured findings to be written to .first-plan/. Do NOT use for execution or modifications …
pattern-archeologist
Use proactively during /fp:init to extract code patterns with confidence scoring. Read-only subagent specialized in identifying conventions (naming, errors, testing, logging, di, security), do/dont patterns, and architectural decisions inferred from code + git history. Each pattern returned with concrete code example…
verification-runner
Use proactively after /fp:execute to verify the implementation works. Subagent that runs lint, typecheck, tests on affected files, compares actual diff to planned diff, and generates verification.md report. Detects regressions and broken builds before reporting success. Read-only on .first-plan/ but can run project's…
gtd-planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gtd:plan-phase orchestrator.
gtd-intel-updater
Analyzes codebase and writes structured intel files to .planning/intel/.
gtd-code-reviewer
Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /gtd:code-review.