skill-optimizer

skill-optimizer is a skill for Claude Code, Codex from SummerSec/SumSec-Skills. It costs 51 tokens per session (3,261 once invoked), scanned A, original, Apache-2.0.

A tool for reviewing and improving Agent Skills, which are instruction files that guide an AI coding agent. It can either prepare changes to a selected skill after confirmation or produce a read-only audit of skills and past sessions.

In plain words
What is it for?
It is for checking skill structure and performance, rewriting descriptions or supporting files with approval, and auditing triggers, usage data, and missing evidence.
Why use it?
It helps explain why a skill does not trigger, does not work as expected, or has unclear instructions before anyone changes its files.

Skill for Claude CodeCodex

Part of the agents-dev plugin — 6 skills, 3 agents, 1 plugin shipped together

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.

agentmods
npx agentmods add skills/summersec/sumsec-skills/skill-optimizer
Any agent
npx skills add SummerSec/SumSec-Skills --skill skill-optimizer
Clone the repo
git clone --depth 1 https://github.com/SummerSec/SumSec-Skills

Made for: Claude Code, Codex.

Or install agents-dev, the plugin that ships this one along with the rest of its 6 skills, 3 agents, 1 plugin.

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 skill-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/summersec/sumsec-skills/skill-optimizer.svg)](https://agentmods.dev/skills/summersec/sumsec-skills/skill-optimizer)
Your own site
<a href="https://agentmods.dev/skills/summersec/sumsec-skills/skill-optimizer"><img src="https://agentmods.dev/badge/skills/summersec/sumsec-skills/skill-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,261 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00051 $0.03261
Opus 5 $0.00026 $0.01631
Sonnet 5 $0.00010 $0.00652
Haiku 4.5 $0.00005 $0.00326

Measured 4d ago against content hash 4979b2be4a6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-optimizer 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.

agents-dev/skills/skill-optimizer/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Optimizer

路径选择

路径 行为 典型触发
A — 结构化改写 读目标 skill → 诊断与计划 → 用户确认后才改 SKILL.md / references / scripts 用户附着或指定路径、说「改 description」「拆 references」「加确认步骤」
B — 会话审计 扫描本机 skill 目录与历史会话 jsonl,只输出报告绝不写 skill 文件 /optimize-skill/skill-audit、「分析我所有 skills」「skill 从不触发」「只审计不要改」

判定: 用户明确「只分析 / 只出报告 / 不要改」→ B。用户点名要改某 skill 且未禁止写文件 → A(无确认仍不得改)。「先看全局再改」→ 先做 B,再在用户要求下对单项切 A

共用规则

  • 官方规范优先(双轨):每次启动先执行下方 Step 0 — Fetch Spec(三级降级:代理 → 直连 → 本地缓存),未完成前禁止进入诊断、计划或改写阶段。
  • 路径 B:只读。 不得修改任何 skill 文件,只交付报告(Step 0 对缓存文件的覆盖是允许的例外,因为它属于 skill 自身的资产更新而非被审计 skill 的修改)。
  • 路径 A:确认门槛。 不得把「审查结论」与「直接改文件」混为一步;未确认不得改目标 skill。
  • 路径 B:八维齐全。 不得跳过 references/session-audit-dimensions.md 中的 4.2、4.3、4.5b、4.8;缺数据写 N/A — insufficient session data
  • 量化与证据: 报告用次数、比例、日期范围;欠触发须引用真实用户原句;description 改写用建议语气并点明依据(静态表条目、官方规范条款或研究结论)。
  • 范围克制: 用户只要某一方向(如只改 description)时,围绕该方向计划,不擅自整 skill 重写;不要为了「全面」把无关 reference 全读进上下文。
  • 路径统一用 ${CLAUDE_SKILL_DIR} 任何「读 / 写 / 引用本 skill 资源」的动作(含脚本、Bash、ReadWriteWebFetch 后落盘)都使用 ${CLAUDE_SKILL_DIR}/... 形式,不写死绝对路径,不写仓库相对路径。

Pipeline 类 skill 的特别处理

当目标 skill 在 Step 2 Review 中被判定为 Pipeline(主模式或次模式),或满足 ≥3 个 workflow-skill-creator 适用信号(≥3 顺序步骤 / 跨步骤状态传递 / 需脚本辅助 / 需进度文件 / 强制顺序、跳步导致失败),按以下规则叠加评审基准:

  • 必读资产${CLAUDE_SKILL_DIR}/../workflow-skill-creator/references/architecture_patterns.md(六大架构模式)与 quality_checklist.md(七维自检)
  • 基准合并:Step 5 Verify 须在 review-checklist.md 之上叠加 workflow-skill-creator 的 quality_checklist;针对编排专门规范遇冲突时以 workflow-skill-creator 为准
  • Plan 输出义务:Step 3 Plan 必须在末段写明「目标 skill 已识别为 Pipeline,对照 workflow-skill-creator 六大模式逐项核对」并列出未达标项
  • 跨 skill 路径:两 skill 同属 agents-dev plugin,故用 ${CLAUDE_SKILL_DIR}/../workflow-skill-creator/... 引用;若日后被拆到不同 plugin,需改为目标 plugin 的解析路径

路径 B 工作流(概要)

  1. Step 0 — Fetch Spec:执行下方「Step 0 详细流程」;本轮基准来自最新抓取或 ${CLAUDE_SKILL_DIR}/references/official-spec-fetch.md 缓存。
  2. 锁定范围/optimize-skill 全量,或 /optimize-skill a b 指定多个 name。
  3. 发现 skill:按 session-audit-dimensions.md 中的目录顺序扫描并去重,读 frontmatter 与步骤结构。
  4. 采集会话:Claude Code / Codex jsonl 字段差异见该文档;Codex 注意「加载 ≠ 已按 skill 执行」。
  5. 跑满八维 + 综合分:表格、权重、报告骨架均见该文档;遇到与官方规范不一致处,须在报告中以「依据:官方规范 §X」标注。
  6. 输出:使用该文档中的 Report Format;P0 / P1 / P2 分级;报告首段写明「本轮使用的官方规范来源(live / cache)+ fetched_at」。

Read the full file on GitHub · 118 lines

Files

What ships with it

5 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.

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. 4d ago First seen · 118 lines · 51 tokens per session scan A 4979b2be4a6b

Subscribe to this mod's changes

skill-optimizer is a skill published in the GitHub repository SummerSec/SumSec-Skills (8 stars, last pushed 20d ago), licensed Apache-2.0. It adds 51 tokens to every session and 3,261 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 2026-08-31.

Related

Other skills, from other repositories

dsh-web-pre-push-checks

Use before pushing, opening or updating a pull request, or claiming dsh-web checks pass. Selects the required repository gates and diff-specific generation, build, and GUI evidence.

zhu1090093659/dsh-web · 45 tokens

dsh-web-documentation

Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.

zhu1090093659/dsh-web · 34 tokens

dsh-sdk-upgrade

Safely select and install a compatible official @deepseek-ai SDK release for dsh plugin projects (dsh-web, dsh-trading, and similar monorepos) from npm using an isolated worktree, explicit cohort review, CI-equivalent validation, and controlled rollout — including syncing the project's declared DSH host-version floor…

zhu1090093659/dsh-web · 176 tokens

dsh-web-sdk-compatibility

Adapt and repair dsh-web after an approved official @deepseek-ai SDK/runtime cohort is selected or installed. Compare public API, type, service-injection, module-table, protocol, and behavior changes; map every change to repository consumers; implement the smallest fixes and durable compatibility contracts; handle…

zhu1090093659/dsh-web · 107 tokens

ov-experience-memory

Retrieve and apply OpenViking Experience memories through the Agent runtime's generic OpenViking search and read tools. Use before or during executable, multi-step, or tool-based work such as coding, file or data changes, configuration, deployment, workflow execution, and failure recovery when prior operational…

volcengine/OpenViking · 78 tokens

dsh-doc-site-sync

Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content…

whitelonng/dshcode · 67 tokens