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 KongFangXun/sofagent --skill cordis-plugin-sofagent-evolvegit clone --depth 1 https://github.com/KongFangXun/sofagentWrote 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/kongfangxun/sofagent/cordis-plugin-sofagent-evolve)<a href="https://agentmods.dev/skills/kongfangxun/sofagent/cordis-plugin-sofagent-evolve"><img src="https://agentmods.dev/badge/skills/kongfangxun/sofagent/cordis-plugin-sofagent-evolve/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/kongfangxun/sofagent/cordis-plugin-sofagent-evolve"><img src="https://agentmods.dev/badge/skills/kongfangxun/sofagent/cordis-plugin-sofagent-evolve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00132 | $0.00807 |
| Opus 5.5 | $0.00053 | $0.00323 |
| Sonnet 5.5 | $0.00026 | $0.00161 |
| Haiku 4.5 | $0.00013 | $0.00081 |
Grade A, and why
cordis-plugin-sofagent-evolve 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.
What it actually says
cordis-plugin-sofagent-evolve
进化面 RSI 独立模块（准入门 / 晋级 / 经验池 / 考核 / 写面审计 / 能力基线 / 透明仓）——经验沉淀（think.md 反思）+ 写面权限窄化（模型只写 memory / skill，控制面写入即拒）（seam: session/event + fs/write-intent）——桥接 @sofagent/think generateThinkEntry
用途
装上之后：① 任务收尾自动写一条 think.md 反思条目；② 写面权限窄化——被治理的执行模型只能写 memory / skill 两类产物，策略 / 注入 / 路由 / 状态 / 审计历史属控制面，写入即拒。 什么时候用：同一个坑反复踩、想让经验留下来被下次检索；或要把「治理面在被治理者可写面之外」落成运行时硬边界。
接入点（seam: session/event + fs/write-intent）：桥接 @sofagent/think，缺依赖时该能力静默跳过；写面窄化判定在插件内（不依赖引擎包，可独立拔插）；接入形态（声明 / 实现）见 SEAMS.md。
RSI 模块定位：准入门 / 晋级 / 经验池 / 考核 / 写面审计 / 能力基线 / 透明仓——v1.5.9 起进化面产品形态从 harness 主干功能改挂本插件（DSH 七款之一，插件位已存在，零迁移成本）；沉淀留主干（数据管道），进化独立成 RSI 插件（决策管道）。换掉本插件 ≠ 失去审计与沉淀（主干完整性不受插件存废影响）。
治理件（可独立拔插）：写面边界 write-surface-boundary.ts（门禁）+ 策展快照 curator.ts（台账——curator 运行前打快照、归档移入 .archive/ 非物理删、动作留痕，与 v1.5.7 退役纪律「归档优先于物理删」同族）。
本插件随 sofagent 主线版本发布（SkillHub 通道：skillhub install cordis-plugin-sofagent-evolve 安装与检索；npm 通道未开通）。版本号与 sofagent 主线对齐。
相关链接
- sofagent 主仓：https://github.com/KongFangXun/sofagent
- 开发日志：docs/changelog/v1.5/v1.5.9.md（章七 进化面插件化）
What ships with it
10 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.
- cordis.patch.yml 816 B
- package.json 1.9 KB
- src/curator.test.ts 6.4 KB runs code
- src/curator.ts 12 KB runs code
- src/index.test.ts 12 KB runs code
- src/index.ts 8.5 KB runs code
- src/trunk-integrity.test.ts 3.9 KB runs code
- src/write-surface-boundary.test.ts 6.6 KB runs code
- src/write-surface-boundary.ts 10 KB runs code
- tsconfig.json 185 B
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.
- 4d ago Changed 63ec378cfd23
- 10d ago Changed c05f246d0726
- 13d ago Changed · +5 lines · +55 tokens per session 3106bf073178
- 16d ago Changed b2b4154fd1b3
- 17d ago Changed 3971a6ed2bfd
- 21d ago Changed b7c5853482a2
- 24d ago Changed 0766f2e6e705
- 26d ago Changed f1e7eb5e920b
- 29d ago Changed 21481d7351b1
- 1mo ago First seen · 26 lines · 77 tokens per session scan A 13fd2d27b3a5
cordis-plugin-sofagent-evolve is a skill published in the GitHub repository KongFangXun/sofagent (54 stars, last pushed 4d ago), licensed MIT. It adds 132 tokens to every session and 807 once invoked, about $0.0005 per session on Opus 5.5. 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
kv-list
List all keys in the Custodian KV store with optional prefix.
kv-get
Retrieve a value by key from the Custodian KV store.
kv-set
Store a key-value pair in the Custodian KV store.
sqlite-query
Run a read-only SQL query against a SQLite database file.
kv-delete
Delete a key from the Custodian KV store.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…