ag-otimizar-harness

ag-otimizar-harness is a skill for Claude Code from andregusman-raiz/a-gusman-claude. It costs 45 tokens per session (1,430 once invoked), scanned B, original, MIT.

A harness-optimization review for reducing the cost and overhead of an agent system. It examines expensive skills, reusable cached instructions, deprecated skills, and low-value tool connections.

In plain words
What is it for?
Use it to rank costly skills from recent sessions, find cache candidates, identify skills that should be retired, and review whether connected tools provide enough value.
Why use it?
It helps show which parts of the agent setup consume the most tokens or resources and where simplification may improve efficiency. Changes can be applied as a focused pull request.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths.

Good fit Use it to rank costly skills from recent sessions, find cache candidates, identify skills that should be retired, and review whether connected tools provide enough value.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andregusman-raiz/a-gusman-claude/ag-otimizar-harness
Install

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.

Any agent
npx skills add andregusman-raiz/a-gusman-claude --skill ag-otimizar-harness
Clone the repo
git clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claude

Made for: Claude Code.

Wrote 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.

agentmods badge for ag-otimizar-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-otimizar-harness/github.svg)](https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-otimizar-harness)
Your own site
<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-otimizar-harness"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-otimizar-harness/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.

agentmods 80×15 button for ag-otimizar-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-otimizar-harness"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-otimizar-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01430
Opus 5 $0.00023 $0.00715
Sonnet 5 $0.00009 $0.00286
Haiku 4.5 $0.00005 $0.00143

Measured 9d ago against content hash a8052e701ed1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

ag-otimizar-harness 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 9d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

1. Lista todas as skills (`ls ~/Claude/.claude/skills/`)
skills/ag-otimizar-harness/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ag-otimizar-harness — Otimizador do harness

Complementa ag-auditar-harness (que diagnostica) com acoes de otimizacao de custo/performance: caching, depreciacao, MCP slimming.

Quando invocar

  • Sob demanda: /ag-otimizar-harness
  • Como sub-fase de /ag-13-limpar-codigo --target=harness
  • Como recommendation gerada por ag-auditar-harness (HCS.mcp_cost baixo)
  • Trimestral via ag-curador-skills

Output

Relatorio em ~/Claude/docs/diagnosticos/harness-optimization-YYYY-MM-DD.md.

Se --apply: PR atomico com markers cache_control: ephemeral aplicados + skills marcadas como deprecated: true.

4 Analises

1. cost_per_skill — Top skills por custo total

Fonte: ~/.claude/projects/*/session-*.jsonl (ultimos 30 dias).

Metodo:

  1. Para cada skill invocada (tool_use com name=Skill):
    • Soma usage.input_tokens + usage.output_tokens da assistant message subsequente
    • Conta invocacoes
  2. Ranking: tokens_total = mean(tokens_por_invocacao) * invocacoes

Output: Top 10 skills caras com decomposicao mean vs frequency.

2. cache_candidates — Skills elegiveis para cache_control

Criterios (do prompt-cache-policy.md):

  • Tamanho >= 300 linhas
  • Conteudo estatico (sem timestamp, IDs, paths dinamicos)
  • Invocada >= 2x por sessao tipica

Metodo:

  1. wc -l em cada SKILL.md
  2. Detecta dinamico: grep {{, \$ARGUMENTS, \$(date, \$(uuidgen etc.
  3. Cross-check com cost_per_skill (frequencia >= 2)
  4. Para cada candidato:
    • Sugere ponto de insercao do marker (apos primeiro ## longo)
    • Calcula tokens economizados estimados (~tokens_per_invocation * (invocacoes - 1) * 0.9)

Action --apply: insere <!-- cache_control: ephemeral --> no ponto sugerido.

Reusa logica do ag-otimizar-cache existente — esta skill orquestra, nao reimplementa.

3. dead_skills — Skills com 0 invocacoes em N dias

Default N=90 dias.

Metodo:

  1. Lista todas as skills (ls ~/Claude/.claude/skills/)
  2. Para cada: grep no transcripts dos ultimos 90 dias
  3. Skills com 0 invocacoes:
    • CONFIRM antes de depreciar:
      • Tem metadata.always_available: true? → skip
      • E referenciada por outra skill ([[name]] em outro SKILL.md)? → skip
      • Foi criada nos ultimos 30 dias? → skip (ainda em adocao)
  4. Sugere depreciacao via metadata.deprecated: true + nota de migracao

Read the full file on GitHub · 152 lines

Changes

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.

  1. 9d ago First seen · 152 lines · 45 tokens per session scan B a8052e701ed1

Subscribe to this mod's changes

ag-otimizar-harness is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 1,430 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

taiyi-ui-design

A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.

Dong90/oh-my-taiyiforge · 35 tokens

taiyi-evolve

A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.

Dong90/oh-my-taiyiforge · 37 tokens

taiyi-diagram-c4

A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.

Dong90/oh-my-taiyiforge · 48 tokens

retrospective-audit

Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…

The01Geek/prflow · 91 tokens

docs

Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…

The01Geek/prflow · 97 tokens

tmux-lane-orchestrator

Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.

vincentkoc/dotskills · 46 tokens