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/stanshy/agenthub/knowledge-feedbacknpx skills add Stanshy/AgentHub --skill knowledge-feedbackgit clone --depth 1 https://github.com/Stanshy/AgentHubWhat 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 | $0.00013 | $0.01151 |
| Opus 5 | $0.00006 | $0.00575 |
| Sonnet 5 | $0.00003 | $0.00230 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
knowledge-feedback 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 3d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
知識回饋
掃描子專案踩坑紀錄，分類並提出公司規範修改建議。
使用方式
/knowledge-feedback
參數
無（操作所有已知子專案）
前置條件
- 必須使用「公司知識管理者」(company-manager) Agent 開啟 Session
- 系統提示詞中已注入子專案清單
執行步驟
階段 1: 收集踩坑紀錄
- 從系統提示詞中取得子專案清單（含絕對路徑）
- 依序讀取每個子專案的
.knowledge/postmortem-log.md - 讀取每個子專案的
.knowledge/coding-standards.md了解專案現況
階段 2: 分類與標記
對每筆踩坑紀錄進行分類：
| 分類 | 判斷標準 | 處理方式 |
|---|---|---|
| 通用問題 | 會在多個專案重複發生、與特定技術棧無關 | 建議更新公司規範 |
| 專案特定 | 僅與該專案的技術選擇或架構有關 | 僅供參考，不更新公司規範 |
| 已處理 | 已在公司規範中有對應規則 | 跳過 |
通用性判斷標準
判斷一筆踩坑紀錄是否具有通用性（應提升為公司規範），使用以下標準：
| 條件 | 判斷 |
|---|---|
| 同類問題出現在 ≥2 個專案 | 強通用 → 必須寫入 postmortem-common.md |
| 問題與框架/語言無關（如 Git 操作、CI 流程） | 通用 → 建議寫入 |
| 問題根因是架構設計或流程規範缺失 | 通用 → 建議寫入 |
| 問題僅因特定版本/套件 bug | 專案特定 → 不寫入 |
| 問題已在公司規範中有對應規則 | 已處理 → 跳過 |
階段 3: 產出摘要報告
輸出以下格式的報告：
# 跨專案知識回饋報告
**掃描日期**: {today}
**掃描專案數**: {count}
## 通用問題（建議更新公司規範）
| # | 來源專案 | 問題摘要 | 分類 | 建議更新的規範文件 | 建議內容 |
|---|---------|---------|------|------------------|---------|
| 1 | {project} | {summary} | {category} | {file} | {suggestion} |
## 專案特定問題（僅供參考）
| # | 來源專案 | 問題摘要 | 備註 |
|---|---------|---------|------|
| 1 | {project} | {summary} | {note} |
## 建議的規範修改
### 修改 1: {file}
**原因**: {why}
**建議新增/修改的內容**:
{diff or new content}
階段 4: 等待老闆確認
- 將報告呈報老闆
- 不得自行修改任何檔案，等待老闆逐項確認
- 老闆可能：全部接受 / 部分接受 / 全部拒絕 / 提出修改意見
階段 5: 執行更新
老闆確認後：
- 修改
.knowledge/company/下的對應文件 - 每個修改都說明：改了什麼、為什麼、影響範圍
- 更新完成後，整理變更摘要
- 對標記為「強通用」或「通用」的踩坑紀錄，寫入
.knowledge/company/standards/postmortem-common.md，格式：
| 日期 | 來源專案 | 分類 | 問題摘要 | 解法 | 相關規範 |
|---|---|---|---|---|---|
| {date} | {project} | {category} | {summary} | {solution} | {reference} |
可寫入的路徑
.knowledge/company/sop/*.md.knowledge/company/standards/*.md.knowledge/company/standards/postmortem-common.md.knowledge/company/templates/*.md
不可寫入的路徑
- 子專案的任何檔案（唯讀）
.knowledge/company/skill-templates/（Skill 模板由開發流程管理）.knowledge/company/project-templates/（專案模板由開發流程管理）
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.
- 3d ago First seen · 117 lines · 13 tokens per session scan A 8ae0f5534b63
knowledge-feedback is a skill published in the GitHub repository Stanshy/AgentHub (200 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 1,151 once invoked, about $0.0001 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-host-e2e-tests
Use when writing, recording, updating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for Claude/Copilot/Codex). Covers adding a cross-provider test…
security-ownership-map
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for…
launch
Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test…
comet-native
Comet Native 工作流。当用户明确调用 /comet-native、要求启动或恢复 Native change，或入口路由到 Native 时使用。.
comet-design
Comet Classic 阶段 2 —— 为 change 产出深度技术 Design Doc。.
data-artist
Create beautiful data visualizations with mathematical elegance, color theory, and narrative design - the "Data is Beautiful" aesthetic.