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 skills add cmdr-chara/codex-toolkit --skill optimize-codebase-performancegit clone --depth 1 https://github.com/cmdr-chara/codex-toolkitWrote 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/cmdr-chara/codex-toolkit/optimize-codebase-performance)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/optimize-codebase-performance"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/optimize-codebase-performance/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/skills/cmdr-chara/codex-toolkit/optimize-codebase-performance"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/optimize-codebase-performance.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 | $0.00040 | $0.00576 |
| Opus 5.5 | $0.00016 | $0.00230 |
| Sonnet 5.5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
optimize-codebase-performance 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 24d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimize Codebase Performance
Optimize measured critical paths, not code that merely looks expensive.
Trigger boundary
Use this skill for a named latency/throughput/CPU/memory/GPU/I/O/startup/rendering/database/bundle/infrastructure-cost problem that can be measured.
Do not trigger for unmeasured cleanup, an unknown correctness failure, migration, broad platform audit, or final release approval.
Required inputs
Resolve the critical path, target metric, representative workload, environment, baseline or baseline plan, correctness invariants, budget/stop condition, working-tree state, and approval state.
Safety baseline
- Preserve uncommitted user work.
- Start with measurement; do not rewrite code on intuition.
- Keep baseline and candidate workloads comparable.
- Never claim a percentage improvement without paired measurements.
- Broad optimization edits stop at a proposal unless already authorized.
Workflow
- Define the target. Name the user/system path, metric, workload, environment, and success/stop criteria.
- Establish the baseline. Use
references/measurement-and-reporting.md; collect enough samples/profiles to distinguish signal from noise. - Attribute the bottleneck. Use
references/bottleneck-playbook.mdacross relevant application, data, dependency, runtime, infrastructure, and UI layers. - Form falsifiable hypotheses. Each candidate change needs evidence, mechanism, expected metric movement, correctness risk, and a measurement that can reject it.
- Propose a bounded batch. Without authorization, stop at
AWAITING_APPROVAL. - Implement one attributable batch at a time. Run focused correctness checks and the same representative benchmark. Revert/revise changes that do not help enough or create unjustified regressions.
- Report honestly. Keep negative results, noise limits, before/after numbers, trade-offs, and residual bottlenecks.
Handoffs and interaction boundaries
Use repository intelligence for unclear hot paths, debugging for incorrect behavior, evolution for version/contract transitions, platform builders for broader product work, security-review if a performance change crosses a security boundary, and verification-and-release for final ship judgment.
What ships with it
3 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.
- 24d ago Changed · -130 lines · -59 tokens per session 235f96652c5d
- 1mo ago First seen · 179 lines · 99 tokens per session scan A c994c6991626
optimize-codebase-performance is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 40 tokens to every session and 576 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
code-coherence-review
Reviews code and plans for logic coherence, correctness, and structural integrity.