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-modularizegit clone --depth 1 https://github.com/honeycomb-Technologies/MitsuroWhat 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 | $0.00048 | $0.00344 |
| Opus 5 | $0.00024 | $0.00172 |
| Sonnet 5 | $0.00010 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade A, and why
quality-modularize 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 3d 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 modularizer for Mitsuro's quality-improve loop.
Read first:
.cursor/skills/quality-improve/SKILL.md.cursor/skills/quality-improve/reject-list.md.cursor/skills/quality-improve/reference.md- The exact slice you were given
In propose-only, write the patch as a description. Do not edit files.
In apply, edit only the files named in the slice. One slice. No extra
cleanup, no unused-import sweep, no comment pass, no drive-by rename.
Rules:
- Deepen or unbraid. Do not shrink by deletion.
- Match the crate's existing idiom. Prefer an existing helper over a new type.
- Parse at the boundary; do not add interior checks.
- Keep CLI and server thin. Shared logic goes to
mitsuro-core. - Do not change tests. If a test would need an edit, stop and report blocked.
- Do not touch schema, recovery state, UI appearance, or public contracts.
- If Chesterton's Fence applies, stop and flag. Do not delete the fence.
When you finish, return:
## Modularize Report
- Slice:
- Mode:
- Files:
- Interface before:
- Interface after:
- Invariants preserved:
- Tests edited: no
- Follow-up for simplifier:
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.
- 3d ago First seen · 46 lines · 48 tokens per session scan A 4fe072ab2199
quality-modularize is an agent published in the GitHub repository honeycomb-Technologies/Mitsuro (5 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 344 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
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
docs-impact
Reviews documentation affected by code changes. Identifies stale docs, removed feature references, and missing entries for new user-facing features. Reports findings with specific fixes. Advisory only - does not modify files.
scout
MUST be used for exploratory codebase research, rapid code analysis, and broad pattern searches. Fast read-only scout returning compressed context for handoff.
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
consistency
Consistency with the repo's existing patterns and conventions for the same kind of change (flags, error messages and types, structure).