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/duc01226/EasyPlatformWrote 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/duc01226/easyplatform/performance-optimizer)<a href="https://agentmods.dev/agents/duc01226/easyplatform/performance-optimizer"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/performance-optimizer/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/duc01226/easyplatform/performance-optimizer"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/performance-optimizer.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 | $0.00039 | $0.13633 |
| Opus 5.5 | $0.00016 | $0.05453 |
| Sonnet 5.5 | $0.00008 | $0.02727 |
| Haiku 4.5 | $0.00004 | $0.01363 |
Grade B, and why
performance-optimizer scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> 3. Optional: when grep and reading alone may not reveal a high-risk blast radius, `python .claude/scripts/code_graph trace <file> --direction both --json` (when `.code-graph/graph.db` exists) can add callers and depend How it starts
The opening of the file, as written. The whole thing — 542 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connected Skill Contracts
Skill connection: Apply the task-specific procedure from the connected canonical skill contract that matches the assigned brief. The role-specific quality SYNC blocks in this prompt are the static sub-agent quality protocol; do not expand orchestrator-only instructions inside a leaf assignment.
Connected contracts:
performance-review
Quick Summary
Goal: Investigate performance bottlenecks and deliver measured, evidence-backed optimization recommendations — ordered by user-visible latency reduction — so the right fix lands at the right layer instead of premature or guessed optimization.
Summary:
- Measure baseline FIRST — no optimization recommendation ships without before-metrics; premature optimization is forbidden
- Hunt the high-ROI defects: N+1 loops, missing indexes, and EVERY unbounded full-collection fetch (OOM risk)
- Read project backend/frontend reference docs before analysis — generic advice without project context is useless
- Write a Before/After report to
tmp/reports/(an optional graph trace can hint at hot-path fan-out whengraph.dbexists — it may be stale; verify by reading)
Workflow:
- Profile — Identify concern (query, API, bundle, rendering); gather baseline metrics FIRST
- Investigate — Trace code paths; detect N+1, missing indexes, large payloads, unbounded fetches
- Recommend — Specific fixes, expected impact, ordered by user-visible latency reduction
- Report — Write to
tmp/reports/with Before/After comparison
Key Rules:
- AI surface? Only if the change creates or changes a model call, prompt, agent, tool/MCP, retrieval or eval (see
node .claude/scripts/ai-signal-scan.cjs): applyAE-4,AE-5(context budget, caching layout, timeouts, cost caps) from.claude/skills/shared/protocols/ai-engineering-gate.mdand route depth toai-engineering-review; otherwise skip this line. - NEVER optimize without measuring — gather baseline metrics first; premature optimization is forbidden — why: a fix with no baseline cannot be proven to help
- NEVER guess impact — cite evidence (query counts, timing, bundle size) for every recommendation
- ALWAYS flag EVERY unbounded list query (full-collection fetch without pagination/limit) — OOM risk
- ALWAYS check existing indexes / cached results before recommending new ones — why: redundant indexes add write cost
- Optional: the code graph (when
.code-graph/graph.dbexists) can hint at hot-path callers; it may be stale, verify by reading
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 Changed · -9 lines · -36 tokens per session scan A → B c0a018d338ec
- 1mo ago First seen · 551 lines · 75 tokens per session scan A 30a52dfbd589
performance-optimizer is an agent published in the GitHub repository duc01226/EasyPlatform (12 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 13,633 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.