Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.
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 zts212653/clowder-ai --skill fresh-context-reviewgit clone --depth 1 https://github.com/zts212653/clowder-aiWrote 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/zts212653/clowder-ai/fresh-context-review)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/fresh-context-review"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/fresh-context-review/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/zts212653/clowder-ai/fresh-context-review"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/fresh-context-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 93 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00071 | $0.02133 |
| Opus 5 | $0.00036 | $0.01066 |
| Sonnet 5 | $0.00014 | $0.00427 |
| Haiku 4.5 | $0.00007 | $0.00213 |
Grade A, and why
fresh-context-review 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SOP 位置: 可选步骤,在
quality-gate(Step ②) 之后、request-review(Step ③a) 之前。 SOP definition:sop-definitions/development.yamlstagefresh_context(optional)。 上一步:quality-gate| 下一步:request-review
Fresh-Context Pre-Review
在正式 cross-cat review 前,用一个 fresh-context session(没参与开发的猫或 author 的新 session)扫一遍 PR diff,产出 finding list。目的是降低正式 reviewer 的认知负荷——reviewer 可以先看 fresh-context findings 再看 diff,节约时间聚焦深层问题。
⚠️ 身份约束(硬规则 — Non-Goal #4)
This is a FINDING GENERATOR, not an approval authority.
- ❌ 不产出 APPROVE / BLOCK / LGTM verdict
- ❌ 不替代 Layer 2/3 named cat review
- ❌ 不签署任何 merge-gate 可识别的放行信号
- ❌ 不影响 Review Provenance Matrix(不产生 localPeerReviewSha / cloudReviewSha)
- ✅ 只产出 "我看到这些 findings"(带签名的 finding list)
核心知识
触发决策表
| PR 类型 | 触发? | 理由 |
|---|---|---|
| 多文件代码改动(≥3 files, ≥50 行 diff) | ✅ 推荐 | 正式 reviewer 认知负荷高 |
| shared/ 或跨包改动 | ✅ 推荐 | 影响面广,early detection 价值高 |
| 状态机 / 生命周期对象改动 | ✅ 推荐 | 转移边容易漏(F229 教训) |
| 纯文档 / ≤10 行 / typo | ❌ 跳过 | 认知负荷已经很低 |
| SKILL.md-only | ❌ 跳过 | 轻量改动,正式 reviewer 足以覆盖 |
| 紧急 hotfix | ❌ 跳过 | 时间约束优先 |
决策权在 author:表格是建议,不是硬规则。Author 自判是否需要 fresh context。
盲点正交性(cross-model 价值)
不同模型族有不同的系统性盲点:
- Claude 族(Ragdoll)的盲点 ≠ GPT 族(Maine Coon)的盲点
- 跨族 fresh-context 的 finding yield > 同族 fresh-context
- 这正是 reviewer delta metric(AC-B2)要量化的价值
流程
前置条件
| 条件 | 检查方式 | 未满足时 |
|---|---|---|
quality-gate 已通过 |
有本轮 gate report | 先跑 quality-gate |
| PR diff 存在 | git diff origin/main...HEAD 有输出 |
没改东西不需要 review |
| Author 判断需要 | 查触发决策表 | 跳过,直接进 request-review |
Ownership: Author 触发
1. Author 完成开发,quality-gate ✅
2. Author 判断是否需要 fresh-context(查触发决策表)
3. 需要 → Author 触发 fresh-context session(见下方 "如何触发")
4. 不需要 → 直接进 request-review
如何触发
方式 A: @ 另一只猫(推荐 — 盲点正交性更高)
在当前 thread @ 一只没参与开发的猫,附上 diff 和 spec:
@{reviewer-handle}
请帮忙做一次 fresh-context pre-review scan:
Branch: {branch-name}
Diff: `git diff origin/main...HEAD`
Spec: `docs/features/F{NNN}-xxx.md`
Plan: `feature-specs/YYYY-MM-DD-xxx.md`
只需要产出 finding list,不需要 verdict。
格式见 cat-cafe-skills/fresh-context-review/SKILL.md "Finding List 格式"。
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 · 184 lines · 71 tokens per session scan A e61534486113
fresh-context-review is a skill published in the GitHub repository zts212653/clowder-ai (2,956 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 2,133 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…