Borrowing it
Nothing to install: this file belongs to morluto/leantoken. 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/morluto/leantoken/main/.agents/skills/optimize-accuracy-first/SKILL.mdgit clone --depth 1 https://github.com/morluto/leantokenWrote 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/morluto/leantoken/optimize-accuracy-first)<a href="https://agentmods.dev/skills/morluto/leantoken/optimize-accuracy-first"><img src="https://agentmods.dev/badge/skills/morluto/leantoken/optimize-accuracy-first/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/morluto/leantoken/optimize-accuracy-first"><img src="https://agentmods.dev/badge/skills/morluto/leantoken/optimize-accuracy-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.00382 |
| Opus 5.5 | $0.00009 | $0.00153 |
| Sonnet 5.5 | $0.00005 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
optimize-accuracy-first 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 1mo 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
Optimize Accuracy First
Use this skill for a performance investigation or an optimization whose benefit needs measurement. Ordinary bug fixes do not need a performance study.
Locate the owner of the work and state the expected improvement before changing it. Preserve the applicable contracts: deterministic results, exact token budgets, Unicode matching, truthful coverage, bounded work, atomic generations, and snapshot consistency. An intentional contract change should be described and tested as such.
Choose evidence that answers the question. Behavioral regressions and differential checks establish correctness; candidate counts can explain work; representative release measurements support latency, CPU, memory, or storage claims. A smaller local timer does not justify worse evidence or more retries. Do not invent agent-success or provider-cost results from retrieval proxies.
Prefer the smallest ownership change supported by the evidence. Remove repeated work or reuse an existing indexed primitive before adding caching, concurrency, or a new abstraction. Keep a simpler design when a proposed optimization has no demonstrated benefit.
Measurement references
Consult only the material relevant to the investigation:
- Measurement matrix: workload and metric choices for search, context, reads, indexing, or caching experiments.
- Repository measurement tools: existing profilers and retrieval datasets.
- Benchmark commands: frozen comparisons and optional paired-agent research.
- Development checks: test ownership and CI.
Report the observed result and its limits. Run checks appropriate to the change; broaden them when a failure, risk, or unresolved question warrants it. Missing optional research data limits performance claims, not permission to finish a validated correctness fix.
What ships with it
2 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.
- 1mo ago Changed · -176 lines · -67 tokens per session cf40ab278dbc
- 1mo ago First seen · 220 lines · 90 tokens per session scan A c581982bae88
optimize-accuracy-first is a skill published in the GitHub repository morluto/leantoken (120 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 382 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
jarvis-use
Use jarvis local-first code intelligence for code structure queries: Tree-sitter declaration outlines and definition navigation, SCIP references and hierarchies, natural-language semantic search, and status capability checks. Prefer over grep for indexed structural questions.
jarvis-issues
Report bugs and request features for the jarvis MCP server via GitHub issues. Use when jarvis errors, an index fails, a limitation bites, or to request an improvement.
codebase-index
Use before answering repository questions about architecture, implementation, symbols, references, dependencies, refactoring impact, data flow, or bugs. Query the local hybrid index first so the agent reads only evidence-bearing file:line ranges instead of scanning the repository, and verify evidence gathered earlier…
codebase-index
Use before answering repository questions about architecture, implementation, symbols, references, dependencies, refactoring impact, data flow, or bugs. Query the local hybrid index first so the agent reads only evidence-bearing file:line ranges instead of scanning the repository, and verify evidence gathered earlier…
jarvis-setup
Install and configure Homebrew jarvis, the local-first structural code intelligence with an always-on Tree-sitter syntax baseline. Use when onboarding, registering the MCP server, or indexing a repo for the first time.
graph
Whole-codebase structural map of the codanna index as one self-contained HTML disc. Wedges per top-level module, concentric rings with hubs at the centre, hover or click a symbol to light its edge web, search, hide or highlight modules, brush a date range on the ribbon timeline (symbols dated by git blame), heatmap of…