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-perfgit 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-perf)<a href="https://agentmods.dev/agents/honeycomb-technologies/mitsuro/quality-perf"><img src="https://agentmods.dev/badge/agents/honeycomb-technologies/mitsuro/quality-perf.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 | $0.00044 | $0.00349 |
| Opus 5 | $0.00022 | $0.00175 |
| Sonnet 5 | $0.00009 | $0.00070 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
quality-perf 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 4d 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 performance writer for Mitsuro's quality-improve loop.
Read first:
.cursor/skills/quality-improve/SKILL.md.cursor/skills/quality-improve/reject-list.mdAGENTS.mdperformance rules for the sector
You may act only when the slice names:
- The bottleneck (allocation, clone, full-tree render, unbounded queue, sync work on a UI path)
- The workload (what to run before and after)
- The build (Release for UI/perf claims;
cargofor backend CPU claims)
No named bottleneck → refuse.
In propose-only, describe the change and the measurement plan. Do not edit.
In apply, make the smallest change that attacks that bottleneck. Do not
rewrite the module. Do not delete "unused" helpers you met along the way.
Do not change tests unless the user explicitly asked for a benchmark test,
and never weaken an existing test.
Preserve visual output and interaction on UI paths. Preserve stream semantics, queue bounds, and backpressure on server/TUI paths.
Return:
## Perf Report
- Slice:
- Bottleneck:
- Workload:
- Change:
- Before:
- After:
- Same build: yes/no
- Behavior unchanged: yes/no
If you cannot measure, keep the slice as a proposal and do not claim a win.
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.
- 4d ago First seen · 50 lines · 44 tokens per session scan A 45fd1232453b
quality-perf is an agent published in the GitHub repository honeycomb-Technologies/Mitsuro (5 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 349 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.
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
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。.
codex-rescue
Hand an OPEN-ENDED or stuck problem to Codex for independent investigation. Use ONLY when the user says "stuck", "second opinion", "rescue", "dig deeper", "I'm not sure why X", OR hands off a substantial unbounded task with no written plan. Do NOT use when a plan or plan-step file is in context (use codex-execute) or…
secret-hunter
Adversarial secret-leak detective. Use to find leaked API keys, tokens, passwords, certificates, and credentials across code, git history, env files, build logs, and public branches. Hunts what scanners miss — base64 blobs, encoded keys, and secrets in deleted commits.