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 uselessspace/freedeepagents-activity-builder --skill activity-reviewgit clone --depth 1 https://github.com/uselessspace/freedeepagents-activity-builderWrote 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/uselessspace/freedeepagents-activity-builder/activity-review)<a href="https://agentmods.dev/skills/uselessspace/freedeepagents-activity-builder/activity-review"><img src="https://agentmods.dev/badge/skills/uselessspace/freedeepagents-activity-builder/activity-review.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 5.1 | $0.00199 | $0.01318 |
| Opus 5 | $0.00100 | $0.00659 |
| Sonnet 5 | $0.00040 | $0.00264 |
| Haiku 4.5 | $0.00020 | $0.00132 |
Grade A, and why
activity-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 8d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activity Review
何时用:活动定义写完或改完、目录验收前。站位:补足
/activity-verify的确定性契约检查与/activity-smoke的运行证据。
语义级、由**你(在场编码 agent)**亲自读文件并推理——不调外部服务、不需要 API key、不碰同步链路。
不做什么(护栏,先记死)
- 只对照活动自己声明的意图(会话里的
## Activity Brief;没有就用manifest.description+ AGENTS.md / host SKILL.md 的显式声明)+ 插件policies/。不引入外部"好活动"参照、不跟别的活动比。 - 不对玩法、题材、风格、口吻做价值判断——那是设计自由。
- 不复判
/activity-verify已确定性查过的契约(schema / manifest 白名单 / 工具 strict / doc↔tools.py 名字漂移)。疑似契约错 → 让用户跑/activity-verify,自己不重判。 - 产出永远是"指出 + 定位 + 给修法",不替开发者重写活动。
- 缺持久化 brief 不报问题——Brief 是会话产物,审存量活动时通常只剩 manifest/skill 文档。
输入与扫描面
输入 = 一个活动目录 activities/<id>/。通读并交叉比对:
manifest.json(description声明的意图、input_modes、capabilities)、runtime.json(data_schema_enabled/ timeout /sse_debug_view/ 模型覆盖等运行配置——不含相位语义)。AGENTS.md+ hostSKILL.md+skills/**(指令与玩法叙事)。tools.py(@tool 真实签名 / docstring)。preview_actions.json、handlers.py、dsl_builder.py与site/的 API client(SPA 交互路径与职责边界)。card_templates/*.json+*.vars.json(卡片契约)。data.schema.json(typed-KV 业务态,若有;相位看这里的业务phase+ 卡模板meta.phase+ host skill 路由,别去 runtime.json 找)。
六维评审
逐维过 references/review-rubric.md:① 指令自洽 ② 卡片编排逻辑 ③ 工具叙事一致 ④ 承诺↔能力匹配 ⑤ 输出纪律落位 ⑥ 意图达成。遇到熟悉写法也要对照 references/prompt-conflict-catalog.md 的反向样例,不能因为历史模板曾这样写就放过。
判级
- CONFLICT(逻辑冲突 / 硬伤) — 两条指令不能同时成立,或指令与契约/工具现实矛盾。
- SMELL(质量异味) — 自洽性弱、易跑偏、承诺与能力不一致但尚未到"兑现不了"。
- NOTE(优化建议) — 可选打磨。
CONFLICT 必须修复后再进入 verify / sync;SMELL / NOTE 是非阻塞建议,可记录接受理由。
输出契约
每条 finding 固定四件套:[维度] · 文件:行 · 问题一句话 · 修法一句话。
## Activity Review — <activity_type_id>
- 评审基准:<一句话复述 Activity Brief 或 manifest/skill 显式声明的意图> + policies
- CONFLICT: <n> SMELL: <n> NOTE: <n>
### CONFLICT
1. [指令自洽] AGENTS.md:L40 要求"每轮必发 result 卡",但 SKILL.md:L88 "无候选时跳过发卡" —— X 情况下二者冲突。
修法:把 result 卡改成有条件发,或在 L40 加例外。
### SMELL
…(同结构)
### NOTE
…
### 下一步
- 有 CONFLICT → /activity-builder 改 → 重新 review;清零后再 /activity-verify。
- 仅 SMELL/NOTE → 自行取舍。
What ships with it
2 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.
- 8d ago First seen · 81 lines · 199 tokens per session scan A 8390a6a4a535
activity-review is a skill published in the GitHub repository uselessspace/freedeepagents-activity-builder (2 stars, last pushed 20d ago), licensed MIT. It adds 199 tokens to every session and 1,318 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…