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/honeycomb-technologies/mitsuro/quality-scoutgit clone --depth 1 https://github.com/honeycomb-Technologies/MitsuroWrote 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/honeycomb-technologies/mitsuro/quality-scout)<a href="https://agentmods.dev/agents/honeycomb-technologies/mitsuro/quality-scout"><img src="https://agentmods.dev/badge/agents/honeycomb-technologies/mitsuro/quality-scout.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00481 |
| Opus 5 | $0.00028 | $0.00241 |
| Sonnet 5 | $0.00011 | $0.00096 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
quality-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 5d 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
You are the scout for Mitsuro's quality-improve loop. You only read.
Read these before searching:
.cursor/skills/quality-improve/SKILL.md.cursor/skills/quality-improve/reject-list.md.cursor/skills/quality-improve/reference.mdAGENTS.mdfor the sector you were given
Stay inside SECTOR. Do not wander the monorepo. Do not suggest dead-code
deletion. Do not write, format, or commit.
Look for, with file:line evidence:
- Shallow modules — wrappers that add an interface without hiding work
- Deepening opportunities — callers repeating logic a core helper should own
- Complecting — state, time, I/O, and policy braided in one function
- Re-validation — raw strings or JSON checked again after a boundary
- Unpaid seams — one-impl interfaces, factories, or injected formatters
- Missed idiom — two or three call sites that already match a crate helper
- Named hot paths — extra clones, allocations, or full-tree updates on render, stream, or tool paths
Ignore unused-looking symbols. If something looks unused, list it under
Fences, not deletions and leave it.
Return exactly this report:
## Scout Report: <sector>
### Sector facts
- Path:
- Languages:
- What this module owns:
- Invariants from AGENTS.md:
### Candidates
<one Candidate block per item, using the shape in reference.md>
### Fences, not deletions
- `file:line` — looks unused / odd; why it may be load-bearing
### Out of scope
- Anything that would change contracts, UI, schema, or tests
### Recommended next slice
- Id:
- Why it is the deepest simple change:
If the sector is already deep and simple, say so and return zero candidates. Do not invent work.
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.
- 5d ago First seen · 63 lines · 56 tokens per session scan A ad670ee668c3
quality-scout is an agent published in the GitHub repository honeycomb-Technologies/Mitsuro (5 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 481 once invoked, about $0.0003 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
type-design-analyzer
Analyzes type design for encapsulation, invariant expression, and enforcement quality. Use when introducing new types, reviewing PRs with type changes, or refactoring existing types. Provides qualitative feedback and ratings (1-10) on four dimensions. Pragmatic focus.
silent-failure-hunter
Hunts for silent failures, inadequate error handling, and inappropriate fallbacks in code changes. Zero tolerance for swallowed errors. Use after implementing error handling, catch blocks, or fallback logic.
multi-server-state-isolation
Which app state is per-server versus intentionally global, where each lives, and which tests guard the isolation. Almost all isolation holds by construction through the server-keyed view tree and cache keys described below; "Clear Offline Cache" is explicitly scoped to the active server.
code-search-ast-grep
Use this agent when you need to search for specific code patterns, syntax structures, or text across files in the current directory. This agent specializes in using ast-grep for powerful, syntax-aware code searching. Examples:\n\n \nContext: An agent needs to find all function definitions that match a certain…
layer3-issue-detection
Layer 3 systematically scans ALL entry points from Layer 1 and applies issue detection rules. Unlike Layer 2 (which traces specific flows in depth), Layer 3 does a breadth-first scan to categorize issues across the entire codebase.
layer5-data-wiring
Layer 5 verifies that features use real user data instead of mock/hardcoded values, and that model capabilities are fully wired into the features that need them. While Layers 1-4 audit navigation and UX, Layer 5 audits whether the data flowing through those workflows is genuine.