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 agentmods add skills/arctan303/creator.skill/self-evolvernpx skills add arctan303/creator.skill --skill self-evolvergit clone --depth 1 https://github.com/arctan303/creator.skillWhat 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 | $0.00074 | $0.00661 |
| Opus 5 | $0.00037 | $0.00331 |
| Sonnet 5 | $0.00015 | $0.00132 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
self-evolver 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 2d 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
自进化技能 (self-evolver)
Purpose
把真实纠正、失败和流程摩擦转成可追溯、可验证的规则改进；先积累证据，再用最小补丁消除可复现缺陷。
Trigger
- 用户明确要求沉淀教训。
- 同类普通信号累计达到 3 次。
- 单次出现安全、隐私、数据损坏、错误发布或越权等严重事件。
- 测试/审查证明规则缺陷，或规则与宿主能力存在可复现冲突。
- 安全检查点发现信号台账存在待处理项。
首次普通外部故障或个人偏好只记录观察，不直接改规则。
Required context
EVOLUTION.md。.codex/evolution/signals.md或.claude/evolution/signals.md；不存在时按模板创建。- 相关
AGENTS.md、Skill、阶段契约和可验证证据。 - 能复现旧行为并验证新规则的 Prompt 行为用例。
Workflow
- 使用“关联 Skill + 问题类别”查重并追加证据，不重复建条目。
- 将普通首次信号标为“观察中”；累计 3 次或严重单次事件转为“待处理”。
- 先修改、合并或删除现有规则，只有结构无法覆盖时才新增。
- 每个应用的补丁至少绑定一个失败前可复现、修改后可验证的 Prompt 用例。
- 运行静态契约和相关行为回归；高风险跨流程变更先请求用户确认。
- 更新台账状态、改动理由和验证证据。
- 补丁登记为可回放条目（修改文件、原规则、新规则、关联用例），供工作流升级时重新评估；禁止只改文件不登记。
Output
- 更新后的信号台账。
- 被修改、合并或删除的规则及理由。
- 关联行为用例与验证结果。
- 需要用户确认的高风险变化和残余风险。
Stop or escalate
- 只有理论偏好、个人习惯、一次性普通外部故障或普通产品需求：不得直接进化。
- 信号证据不足但影响主流程或多个 Skill：标为“待确认”。
- 变更会降低审查、隐私、安全或发布标准：必须用户确认。
- 无法构造回归用例：保留信号，不应用补丁。
References
执行前读取 stage-contract.md。
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.
- 2d ago First seen · 56 lines · 74 tokens per session scan A daa20ca2aaf7
self-evolver is a skill published in the GitHub repository arctan303/creator.skill (20 stars, last pushed 28d ago), licensed MIT. It adds 74 tokens to every session and 661 once invoked, about $0.0004 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 skills, from other repositories
agent-sop-author
Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.
skill-creator
Create or improve Zhin Agent skills (SKILL.md). Use when asked to add a skill, write SKILL.md, document a repeatable agent workflow, or refine skill frontmatter/keywords. Triggers: 创建技能, 写 SKILL, skill-creator, 加 skill.
agent-team
Build low-context multi-agent teams with durable handoff, independent review, and user gates. Use when a project needs separate management, execution, and review roles.
agent-team
Build low-context multi-agent teams with durable handoff, independent review, and user gates. Use when a project needs separate management, execution, and review roles.
ai-communication-network
Implement inter-agent communication for tactical coordination.
skill-forge
Generate a new skill from a simple prompt, then run an enhancer pass to tighten trigger rules, workflow, and output quality.