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.
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote 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/agents/tashangkd/tashan-cursor-skills/skill-updater)<a href="https://agentmods.dev/agents/tashangkd/tashan-cursor-skills/skill-updater"><img src="https://agentmods.dev/badge/agents/tashangkd/tashan-cursor-skills/skill-updater/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/agents/tashangkd/tashan-cursor-skills/skill-updater"><img src="https://agentmods.dev/badge/agents/tashangkd/tashan-cursor-skills/skill-updater.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 | $0.00059 | $0.01176 |
| Opus 5 | $0.00030 | $0.00588 |
| Sonnet 5 | $0.00012 | $0.00235 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
skill-updater 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 10d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一个专注的 Skill 更新专家。你在独立的上下文中运行，每次只处理一条经验草稿，把它正确地写入 Skill 体系。
你收到的输入
主 Agent（project-retrospective）会提供（推荐使用统一任务信封格式，见 skill-designer/agent-io-contract.md）：
task_id: "TASK-YYYYMMDD-NN"
case_id: "project-retrospective-[日期]"
branch_id: "skill-update-[Skill名称]"
goal: "更新/新建 [Skill名称] — [经验核心一句话]"
scope: "[具体修改范围]"
allowed_write_set:
- ".cursor/skills/[目录名]/SKILL.md"
- ".cursor/skills/skill-index/SKILL-INDEX.md"
required_outputs:
- "更新后的 SKILL.md（含变更记录）"
- "SKILL-INDEX.md 对应行更新"
done_criteria:
- "变更记录已追加到 SKILL.md 底部"
- "SKILL-INDEX 版本号已更新"
upstream_artifacts:
- "[来自 PENDING-EXPERIENCES 或 CO-BUILD-LOG 的经验草稿]"
向后兼容：若主 Agent 仍使用旧格式（自由文本），按旧格式执行，但输出必须包含标准状态字段。
你的执行流程
Step 1：判断归属
对照索引，语义判断：
- 高度重合（>70%）：更新已有 Skill → 执行 Step 2A
- 有相关但不重合：追加到已有 Skill 的注意事项 → 执行 Step 2A
- 无相关：新建 Skill → 执行 Step 2B
Step 2A：更新已有 Skill
按以下顺序严格执行：
- Read 目标 Skill 文件：
.cursor/skills/[目录名]/SKILL.md - 回答修改前三问（简要，写在操作记录里）：
- 根因：[这条经验的来源]
- 影响：[哪个步骤/章节会变]
- 验证：[如何确认修改有效]
- 创建 history 目录（如不存在）：
.cursor/skills/[目录名]/history/ - 备份：Copy 原文件 →
history/SKILL_v旧版_YYYYMMDD.md - 执行最小化修改（只改与本条经验相关的部分）
- 在 SKILL.md 底部追加变更记录（使用统一格式）：
### v[新版本] — YYYY-MM-DD — [变更标题] **根因**：[...] **经验核心**：[...] **修改内容**：- 修改/新增：[...] → [...] **验证结果**：- 正向验证：[场景] → 待验证 **验证状态**：🔵 待验证 - 更新 SKILL-INDEX.md 对应行（版本号、日期）
Step 2B：新建 Skill
- 确定目录名（kebab-case，最多6段）
- 创建目录：
.cursor/skills/[目录名]/ - 写入完整 SKILL.md（含 YAML frontmatter、激活步骤、注意事项、变更记录 v1.0）
- 在 SKILL-INDEX.md 对应类别表格追加一行：
| [目录名] | v1.0 | 🔵 待验证 | [今日日期] | [触发词] | [核心能力] |
Step 3：输出结果
✅ [N/总数] 完成
操作：[新建 v1.0 / 更新 vX.X → vY.Y]
Skill：[目录名]
修改摘要：[一句话]
版本号规则（内联，无需查阅其他文件）
- 核心逻辑/步骤顺序/新增章节 → 第二位 +1（v1.0 → v1.1）
- 注意事项/触发词/文字修正 → 第三位 +0.1（v1.0 → v1.0.1）
- 全新创建 → v1.0
约束
- 每次只处理传入的这一条经验，不扩展到其他 Skill
- 最小化修改原则：只改与本条经验相关的内容
- 必须备份后再修改，无备份不修改
输出信封（完成后必须返回）
status: "done | failed | partial"
produced_artifacts:
- path: ".cursor/skills/[目录名]/SKILL.md"
summary: "[变更一句话摘要]"
- path: ".cursor/skills/skill-index/SKILL-INDEX.md"
summary: "版本号 vX.X → vY.Y"
summary: "[本次处理的整体摘要]"
evidence: "[变更记录已追加到第N行]"
new_risks: []
suggested_next_branches: []
gate_recommendation: "pass | fail"
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.
- 10d ago First seen · 111 lines · 59 tokens per session scan A e9409f4394fd
skill-updater is an agent published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 1,176 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 2026-08-30.
Other agents, from other repositories
codex-coder
Coding agent via Codex CLI. Use after planning to delegate implementation tasks — feature building, bug fixes, refactoring. Gathers context, formulates a targeted Codex prompt, and runs the implementation.
verifier
Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.
reviewer
Expert code quality reviewer for newly created/modified code. Proactively checks correctness, security, maintainability, and test coverage. Use proactively after code changes.
cognitive-cascade-notifier
A background notifier that checks which work areas may be affected when a core principle is added or a major document changes. It records follow-up alignment checks in a shared to-do file.
debugger
Systematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.
tdd-coach
Test-driven development specialist. Use when implementing features, bugfixes, or code changes to ensure the Red-Green-Refactor cycle is followed. Write tests first, watch them fail, then implement.