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-issue-resolvenpx skills add lync-cyber/CataForge --skill framework-issue-resolvegit clone --depth 1 https://github.com/lync-cyber/CataForgeWrote 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/lync-cyber/cataforge/framework-issue-resolve)<a href="https://agentmods.dev/skills/lync-cyber/cataforge/framework-issue-resolve"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/framework-issue-resolve.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.02367 |
| Opus 5 | $0.00042 | $0.01184 |
| Sonnet 5 | $0.00017 | $0.00473 |
| Haiku 4.5 | $0.00008 | $0.00237 |
Grade A, and why
framework-issue-resolve 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
框架 issue 闭环消化 (framework-issue-resolve)
五步闭环
1. 拉取 (fetch) → cataforge issue triage [--dry-run]
2. 审查分析 (analyze) → draft 落 docs/reviews/triage/SKILL-IMPROVE-<id>-issue-<N>.md
3. 给修复意见 (propose)→ draft 内 verdict + rationale + 修复路径
4. 实施 (implement) → feature branch + Edit + commit + PR(标准 dev 流程)
5. 关闭 (close) → cataforge issue close <N> --verdict <v> [--pr <P>] [--reason ...]
每步之间是 maintainer 强制 checkpoint:自动化只跨 1↔2 和 5;3↔4 是人工 go/no-go。
能力边界
- 能做: 拉取 + Layer 1 字段解析 + 草稿渲染 + close 模板化(统一文案)
- 不做: Layer 2 语义分析(仍是基于正则的字段抽取);自动跨过 maintainer 实施 PR;自动改 issue label(用户/maintainer 手动)
审查与修复纪律
Step 2–4 定位与修复前按此自检,规避 LLM 常见误区(「做 A 而非 B」):
- 先在当前代码复现,再判根因:用最小路径验证症状在当前版本仍可复现,而非凭 issue 描述或
confirmedverdict 直接动手 —— verdict 是 Layer 1 事实核查,不代表根因已定。 - 先查是否已实现:动手前搜索目标逻辑是否已存在(可能在另一层或另一入口未接通),而非假设缺失即新写。
- 修根因而非症状:沿调用链 / 数据流定位最深层原因(如 SSOT 违背、生产方与消费方解析不对称),改产生缺陷的一方,而非让消费方容忍坏输入。
- 验证 reporter 建议的前提:其修复方向可能机制不可行、已被实现或仅触及症状;先核实再决定采纳 / 替代 / 否决,不照搬。
- 核全部入口:某能力已存在却仍报缺陷时,确认所有调用路径都接通它,而非只改单一入口。
- 修复设计以收敛为准绳:修复应减少而非增加同一语义在系统中的实现数——不变量只保留一个实现点,置于全部路径必经的最窄处;复用既有机制与信号,删除无生产者 / 无消费者的路径;而非在各入口分别贴补丁、另造检测副本或为死路径保留兼容。
- 可复现缺陷先写失败测试:先写钉住症状的失败测试(RED)再修(GREEN),把回归固化。
输入规范
framework.json#upgrade.source.repo— 拉取目标framework.json#feedback.gh.labels— 默认 label 过滤集合- 本地
.cataforge/skills/*和.cataforge/agents/*— id 核对 cataforge.__version__— reported_version vs installed_version 比对
输出规范
Step 2 草稿 frontmatter
---
id: skill-improve-<target_id>-issue-<N>
doc_type: skill-improve
status: draft
source_issue: <N>
source_url: https://github.com/<owner>/<repo>/issues/<N>
reported_version: <X.Y.Z>
installed_version: <cataforge.__version__>
verdict: <见下表>
target_id: <skill/agent id, 或 source 文件名>
target_kind: skill | agent | source | schema | mixed | aggregate
target_path: <可选>
rationale: "..."
---
verdict 五态
| verdict | 触发 | 后续动作 |
|---|---|---|
confirmed |
引用了存在的 skill/agent/源文件 + reporter version 持平 | 写草稿;步骤 4 实施修复;步骤 5 close --verdict fixed |
wontfix-by-design |
maintainer 判定下游误解了主动设计(如带点 doc_id 被框架主动拒绝) | 草稿写出主动设计的 evidence;步骤 5 close --verdict wontfix --reason ... |
already-fixed |
reported_version < installed_version(自动判定) | 不写草稿;步骤 5 close --verdict already-fixed --pr <历史 PR> |
needs-repro |
body 缺 cataforge --version 行 |
不写草稿;评论要求 reporter 重跑 cataforge feedback bug --gh,加 label needs-repro(手动) |
unrelated |
不像 feedback bundle | 不写草稿;可手动 close 为 off-topic |
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 First seen · 159 lines · 84 tokens per session scan A 81ee7d09ba95
framework-issue-resolve is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 2,367 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
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…