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 andregusman-raiz/a-gusman-claude --skill ag-otimizar-cachegit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/ag-otimizar-cache)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-otimizar-cache"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-otimizar-cache/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/andregusman-raiz/a-gusman-claude/ag-otimizar-cache"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-otimizar-cache.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 3 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 36 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00050 | $0.01620 |
| Opus 5 | $0.00025 | $0.00810 |
| Sonnet 5 | $0.00010 | $0.00324 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
ag-otimizar-cache 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 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.
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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AG-OTIMIZAR-CACHE — Auditor de Prompt Cache
Invocacao
/ag-otimizar-cache # Dry-run: reporta candidatos (default)
/ag-otimizar-cache --dry-run # Explicito — so reporta, nao altera
/ag-otimizar-cache --apply # Aplica markers nos arquivos
/ag-otimizar-cache skill:ag-1-construir # Audita apenas 1 skill
/ag-otimizar-cache all # Audita todas as machines + reference skills
O que faz
Auditoria em 3 fases:
SCAN -> ANALYZE -> REPORT [-> APPLY se --apply]
- SCAN: Lista todas as skills em
~/.claude/skills/ag-*/SKILL.md+ag-referencia-*/SKILL.md - ANALYZE: Para cada skill, calcula tamanho, identifica blocos estaticos, detecta candidatos
- REPORT: Relatorio com tokens estimados antes/depois por skill
- APPLY (so com
--apply): Injeta markers<!-- cache_control: ephemeral -->nos pontos corretos
Criterios de candidato (ver prompt-cache-policy.md)
Uma skill e candidata se:
- Corpo SKILL.md >= 300 linhas de instrucoes
- Tem bloco estatico longo (tabelas, checklists, pipelines) antes de secao dinamica
- Invocada frequentemente (machines principais: ag-0 a ag-9, ag-meridian, ag-sentinel, ag-fortress)
- NAO tem
cache_policy.enabled: falseno frontmatter
Estimativa de tokens
Heuristica: tokens ≈ chars / 4 (aproximacao conservadora para PT-BR + codigo misto).
Calculo de economia:
tokens_cacheados = tokens(bloco antes do marker)
tokens_nao_cacheados = tokens(bloco apos o marker)
economia_por_hit = tokens_cacheados × custo_input (custo de cache hit < custo de input normal)
break_even = 2 invocacoes dentro de 5 min
Obs: valores exatos dependem da API Anthropic — esta skill reporta estimativas por heuristica.
Ponto de insercao do marker
O marker vai IMEDIATAMENTE apos o ultimo bloco estatico e ANTES de qualquer secao dinamica.
Sinais de "secao dinamica" (interrompe o bloco cacheavel):
- Secoes com
{PROJECT_ROOT},{ARGS},{USER_INPUT} - Secoes de "Invocacao" com exemplos variaveis
- Secoes de "Output" com placeholders de run
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.
- 9d ago First seen · 155 lines · 50 tokens per session scan A 644322b83429
ag-otimizar-cache is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 1,620 once invoked, about $0.0003 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
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.
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.
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.
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…
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…
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.