Borrowing it
Nothing to install: this file belongs to irahardianto/rugged-gemini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/irahardianto/rugged-gemini/main/.gemini/skills/perf-optimization/SKILL.mdgit clone --depth 1 https://github.com/irahardianto/rugged-geminiWrote 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/skills/irahardianto/rugged-gemini/perf-optimization)<a href="https://agentmods.dev/skills/irahardianto/rugged-gemini/perf-optimization"><img src="https://agentmods.dev/badge/skills/irahardianto/rugged-gemini/perf-optimization.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 | $0.00031 | $0.01909 |
| Opus 5 | $0.00015 | $0.00955 |
| Sonnet 5 | $0.00006 | $0.00382 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
perf-optimization 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimization Skill
When to Use
- Profiling data available (pprof, flamegraph, py-spy, Chrome/Dart DevTools)
- User requests perf analysis
- Benchmark regression detected
- New feature touches hot path
Methodology
Profile → Analyze → Prioritize → Optimize → Benchmark → Improvement? → Verify & Ship (or re-prioritize)
1: Profile
Language-appropriate tool (load languages/*.md). Output: raw CPU/heap/trace profile.
2: Analyze
- Focus
cum— total cost of fn + everything it calls. Finds expensive flows. - Contextualize
flat— fn's own cost. Trace runtime fns (GC, malloc) UP to user code. - Ignore runtime noise — scheduler overhead always appears. Note GC pressure but don't "fix" scheduler.
- Separate benchmark artifacts — test harness allocations (httptest, ResponseRecorder) aren't production cost.
Output: docs/research_logs/{component}-perf-analysis.md
3: Prioritize
| Priority | Criteria |
|---|---|
| Do first | Low risk, high impact (caching, pre-alloc, fast-reject) |
| Do second | Medium risk, high impact (library swap, algorithm change) |
| Do last | High risk, high impact (major refactor, custom impl) |
| Skip | Any risk, low impact (micro-opt below noise) |
Rule: >1 day AND <20% hot path savings → defer.
4: Optimize
One fix at a time. TDD (Red→Green→Refactor). Run tests. Benchmark immediately. Never batch multiple opts in one commit.
5: Benchmark
Same config before/after (-benchtime, -count, machine load). Report: ns/op, B/op, allocs/op.
6: When to Stop
- Remaining CPU in hardware assembly (AES-NI, SIMD) — can't beat hardware
- Remaining allocs from runtime (GC, goroutine stacks, HTTP internals)
- Fix requires custom impl of audited library — security risk > perf gain
- Improvement <5% and within noise
Pattern Catalog
Result Caching
Symptom: Repeated expensive computation with identical inputs. Fix: Bounded LRU with TTL. Safety: Security-sensitive results: re-validate expiry, bound cache size (DoS), TTL < credential validity.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 202 lines · 31 tokens per session scan A 4f514cc68485
perf-optimization is a skill published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 1,909 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.