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/lync-cyber/cataforge/framework-feedbacknpx skills add lync-cyber/CataForge --skill framework-feedbackgit clone --depth 1 https://github.com/lync-cyber/CataForgeWhat 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 | $0.00128 | $0.01653 |
| Opus 5 | $0.00064 | $0.00826 |
| Sonnet 5 | $0.00026 | $0.00331 |
| Haiku 4.5 | $0.00013 | $0.00165 |
Grade A, and why
framework-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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
框架反馈打包 (framework-feedback)
能力边界
- 能做: 聚合
cataforge --version+doctor+ 最近 N 条 EVENT-LOG +CORRECTIONS-LOG deviation=upstream-gap+framework-reviewLayer 1 FAIL 摘要；渲染为 markdown；脱敏路径；通过--print/--out/--clip/--gh四选一发出 - 不做: 修复发现的问题（仅打包反馈）；处理下游项目自身的产品反馈（与本 skill 无关）；自动发起 GitHub issue（除非显式
--gh，且需本机已装并登录gh）
输入规范
- kind:
bug|suggest|correction-export - 项目根下的
.cataforge/+docs/EVENT-LOG.jsonl+docs/reviews/CORRECTIONS-LOG.md（任一缺失都降级为部分 bundle，不阻断） cataforge.core.feedback（assembler；CLI 与本 skill 共用同一份逻辑）
输出规范
- 默认: stdout 渲染 markdown body
--out PATH: 写到指定文件（相对路径解析在项目根下）- 上游 issue 模板:
.github/ISSUE_TEMPLATE/feedback-from-cli.yml（字段与本 bundle 一一对应，方便上游分诊） - EVENT-LOG: 每次运行写一条
state_change事件（record-to-event-log: true），ref=skill:framework-feedback/framework_feedback
推荐触发路径
framework-feedback 是按需触发的反馈打包 skill，不进入业务流程主循环。推荐的合规触发面：
- 用户手动:
cataforge feedback bug --gh（或suggest/correction-export） - orchestrator 自动: 当累计
upstream-gap数 ≥RETRO_TRIGGER_UPSTREAM_GAP_DEFAULT时，orchestrator 调起cataforge skill run framework-feedback -- correction-export --out docs/feedback/<ts>.md（reflector 只读，本 skill 需要shell_exec，故由 orchestrator 持有）。落盘后由用户决定是否上报 - doctor 报告 FAIL 后:
cataforge feedback bug --print | tee docs/feedback/doctor-fail-<ts>.md - 不要: 让 reviewer / implementer 在业务流程内自动调起（与业务 review 报告不是同一资源）
操作指令: 上游反馈打包 (feedback)
Step 1: 触发选择 kind
- 出现可复现 bug / 异常退出 / 部署后失败 →
bug - 框架行为符合预期但流程笨重 / 缺特性 →
suggest - 累计多条
deviation=upstream-gap纠偏 →correction-export
Step 2: 调用 Layer 1 打包脚本
调用约定（单一入口）: 一律通过 cataforge skill run framework-feedback -- <kind> [--summary ...] 触发，由框架解析 SKILL.md 元数据并派发到 builtin 脚本。不得直接 python .cataforge/skills/.../scripts/*.py——该路径为框架内部实现细节，不保证存在。
执行示例:
# bug 反馈到 stdout
cataforge skill run framework-feedback -- bug --summary "deploy 后 hook 不触发"
# 建议写盘等待复核
cataforge skill run framework-feedback -- suggest \
--summary "希望支持 --dry-run 预览" \
--out docs/feedback/suggest-$(date +%Y%m%d).md
# 上游反馈聚合 (仅当 upstream-gap 数 ≥ threshold；缺省 threshold = RETRO_TRIGGER_UPSTREAM_GAP_DEFAULT)
cataforge skill run framework-feedback -- correction-export
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 · 90 lines · 128 tokens per session scan A 86e8759cd9da
framework-feedback is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 1,653 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…