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 RainFlashPoint/capital-agent-skills --skill harvest-experiencegit clone --depth 1 https://github.com/RainFlashPoint/capital-agent-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/skills/rainflashpoint/capital-agent-skills/harvest-experience)<a href="https://agentmods.dev/skills/rainflashpoint/capital-agent-skills/harvest-experience"><img src="https://agentmods.dev/badge/skills/rainflashpoint/capital-agent-skills/harvest-experience/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/rainflashpoint/capital-agent-skills/harvest-experience"><img src="https://agentmods.dev/badge/skills/rainflashpoint/capital-agent-skills/harvest-experience.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 | $0.00060 | $0.04114 |
| Opus 5 | $0.00030 | $0.02057 |
| Sonnet 5 | $0.00012 | $0.00823 |
| Haiku 4.5 | $0.00006 | $0.00411 |
Grade A, and why
harvest-experience 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 11d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harvest & Inject Coding Experience
这个 skill 让本地 CLI 会话和 capital-agent 知识层形成闭环：登记会话 → 注入 → 编码 → 沉淀 → 结束。 它不改变正常编码方式，只补充轻量元数据事件；绝不上传代码正文。
团队平台链路的前置是 MCP server capital-agent 已在本 CLI 注册（提供 enrich_context、record_experience、search_knowledge 等工具）。必须区分两种失败：团队模式已配置但当前会话根本没有暴露 MCP 工具时，按 cap-status.mode=restart_required 让用户选择重启或本次本地继续；本地继续返回 local_fallback_explicit，跳过平台连接且不写 Outbox，但任务完成后仍形成本地经验原稿。MCP 工具已经加载、但远端调用临时失败时，正常编码可离线继续，本轮已经形成的 Task/Artifact/Delivery/Experience/Skill Event 元数据必须进入 .cap/outbox.jsonl，不能静默丢失。
若 scripts/cap-status.mjs 返回 mode=local_explicit（配置 CAPITAL_AGENT_MODE=local）或 mode=local_fallback_explicit（用户只为本次任务明确本地继续），只跳过平台半链路：不登记平台会话、不调用 MCP、不创建 Task / Artifact / Delivery / Experience 事件，也不写或重放 Outbox。实现与验证完成后仍按第 2 节编写并校验本地 .cap/experience.md，让 Git 历史保留可复用项目记忆；本地测试和评审结论不得包装成 Server Gate。
1. 会话开始 —— 登记 + 注入
若当前目录属于 Git 仓库，开始实质工作前静默运行仓库自带的 scripts/install-git-governance.mjs（从本 skill 所属 package 根定位）。它幂等安装 prepare-commit-msg，保留并先执行项目原 Hook，把 .cap/STATE.md 中有效的 Task/Session 自动追加到 Commit，并在代码提交时检查 .cap 研发产物没有被遗漏或本地 exclude；安装失败时降级，不阻塞编码。不要要求用户手工安装或理解 Hook。
若 MCP 提供 create_or_attach_task，优先按 references/platform-task-loop.md 创建/复用统一 Task；把返回的 task_id、session_id 写入 .cap/STATE.md。当 cap-status 已解析出活动 follow-up Task 时，必须切换到该 Task 并新建 Session，不能沿用已结束父 Task 的 session_id。仅当已加载的兼容 MCP 只提供旧接口时才退回 start_skill_session。团队模式下 MCP 工具集合完全缺失属于 restart_required；用户选择本次本地继续后跳过平台登记和注入，工具存在但调用失败才进入离线补报流程。
在开始实质编码前，用本次任务的意图调用一次 MCP 工具 enrich_context：
agent_type: 按任务性质选dev（改代码）/prd（理需求）/review/testinput: 用户这次的需求/意图原文repo_url: 当前仓库地址（git remote get-url origin或本地路径，用于统计复用率归因）；首次外发前必须移除 URL 中的用户名、密码和 Token，注入与沉淀复用同一份净化结果。session_id: 团队模式使用 Task 返回的会话标识task_id: 新版 Server 支持时同时传统一 Task ID；Server 会把本次真实返回的知识 ID 持久化到该 Task 的注入台账。旧客户端未传时可由session_id反查，反查失败只保留曝光统计，不能形成精确采纳证据。
把返回的经验内容作为上下文纳入你的方案，不要照搬无关内容。若返回为空，正常编码即可。
团队模式下，create_or_attach_task 会同时返回冻结知识快照的最小 knowledge_snapshot.items（文档 ID、标题、来源类型和命中原因），enrich_context 会在每条可归因知识旁标出 知识ID。冻结快照是允许集合，Server 注入台账是本轮真实看到的集合；Delivery 声明是客户端确认采用的集合。只有三者交集才能成为精确采用。标题相似但 ID 不同、只在其中一边出现，或属于代码图谱/项目画像而没有快照文档 ID 时，都不能声称采用。
What ships with it
3 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.
- 11d ago First seen · 135 lines · 60 tokens per session scan A 1f8a1f7a6a36
harvest-experience is a skill published in the GitHub repository RainFlashPoint/capital-agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 4,114 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.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.