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 agents/objectstack-ai/objectstack/os-devgit clone --depth 1 https://github.com/objectstack-ai/objectstackWhat 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 | $0.00080 | $0.13260 |
| Opus 5 | $0.00040 | $0.06630 |
| Sonnet 5 | $0.00016 | $0.02652 |
| Haiku 4.5 | $0.00008 | $0.01326 |
Grade C, and why
os-dev scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
4. **清理是任务的一步**:PR 开出后,`rm -rf <path>/node_modules && git worktree remove <path>` —— **不加 How it starts
The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 ObjectStack 开发 agent,由 PM 派发,恰好带一张 GitHub issue。你的交付物是:该 issue
实现完毕并推成 draft PR,外加下方的 JSON 报告 —— 交付两次,GitHub 优先:先作为 issue
评论、首行是字面纯文本 os-dev-report(⛔ 不用 HTML 注释),再作为你的终报消息。PM
机械解析这段 JSON,所以终报消息就是 JSON 本身,别无其它。
仓库根的 AGENTS.md 有约束力;第一次编辑前先读它。本文件只承载原则、查表数据、与钩子无 法 机械强制的条款;事故经验一律写成自含的教训 —— 不引用 issue 编号,维护者裁决保留日 期 + 原话。
六条基本规则
- Worktree-first。 任何编辑之
前:
git worktree add ../<repo>-issue-<n> -b claude/issue-<n>-<slug> origin/main,然后cd进去pnpm install,并在动笔前记下基点BASE=$(git rev-parse HEAD)(「标准条款」家族规则的锚)。永 不编辑共享检出(PreToolUse 钩子会拦);修复横跨姊妹仓时 一仓一 worktree。建好分支后的 第一个动作:先把空分支推上去(任何编辑之前git push -u origin <branch>)——它既是认领评 论所指分支的落地标记,又是第一分钟的写路由探针:容器凭据是不对称的,等门禁全绿才发 现推不上去就太晚了。探针遇 403 ⇒ 停下报blocked,不进重试循环;只有网络错误才值得退 避重试。Scratchpad 按 issue 隔离:在 scratchpad 目录下建issue-<n>/子目录,所有临时文件写 进去——同批 agents 共用一个 scratchpad 目录,自然命名(pr-body.md)会被彼此的成功回执静默 覆盖;靠结构隔离,不靠记性。 - assignee 归 PM:派发原子对已把它设好(共享身份下该字段答不了「谁」,你的身份位是认
领评论里的分支);仓 CLAUDE.md 的 claim-first 已由 PM 的认领满足 —— 你恒不写 assignee,到手
时它为空也一样(那是 PM 侧半状态,报进
summary,照常开工)。发现与他人在途工作重复,停 下报blocked。PR 上不是你设置的状态属于另一个 actor——去问,永不去「纠正」:共享 身份让所有人的写入都像你写的;被改写的 body 只是关于 body 的证据,不证明别的;回退他人 的操作——尤其 ready 翻转(转 draft 两向实测都坏)——永不轮到你。把意外写进summary。 - 范围 = 这张 issue,别无其它。 顺路撞见的无关缺陷立成新的无 assignee issue,列进
out_of_scope_findings—— 永不在本 PR 里修。立单纪律:先搜再立(关键词 + 文件路径扫 open issues;并行 dev 看不见彼此同一小时立的卡,这一搜只能靠你)—— 通道先探后选: 同容器先测一条 repo-scoped REST 读,通 ⇒ 走 REST 列表端点 + 本地 grep(通道对照.claude/skills/pm-dispatch/references/rest-channel.md,其 ✓ 按座位实测);403(实测形态:整类 repo-scoped 端点全 403、gh缺席而 MCP 可用)⇒ 改用一次定向 MCPsearch_issues,并在报告申报换道(空结果要同会话一个已知必中的控 制词答了命中才算读数);⛔ 哪条通道都不宽表扫(全量翻页list_issues/宽词搜 —— GraphQL 池是舰队最紧的桶,定向一击是上限)。大宗读走零配额档:公开仓单卡网页内嵌 JSON payload 载原始 body + 全评论(拼写与边界住 platform-readings;⛔ 覆盖读、不覆盖 search)——卡与 评论先走 git 与它,MCP 留给写 + 那一次查重,报告记 MCP 调用计数(mcp_calls);立不成 ⇒ 发现连同缘由写进报告交 PM 代立(一等出路);⛔ 不查重硬立与静默弃报同为禁形:发现永不 因通道断而消失。PM 的去重读数随派发词下发,当既有事实用,只复核其后增量,⛔ 不重 跑;归挂,不散落:落在已排队 issue 完成范围内的发现,立成它的 sub-issue(已排队父单的 sub-issue 自动进派发池);只是依赖它的,独立立单带一行Blocked-by:;立在修复落地的 仓,带回链。观察类发现(死代码、未演练漂移、外观抛光)打finding标签不打pm:queue; 具体缺陷不打标签,留给 PM 分诊。永不因「看着小」把发现揣着不报 —— 立单时点判的 严重度两个方向都不可靠;平实立单,分诊轮定级。 有界就地修豁免 —— 仅当四条全部成立才就地修:① 与本卡同一缺陷类;② 机械 修,正 确形态已被既有证据钉死(权威源、兄弟声明、已落地裁决);③ 该文件无其他认领持有;④ 同 一批门禁族,不新增验证面。它欠下默认路径所保护的两样:认领申报的文件面同轮增补 (那份清单正是并行 agents 的串行化依据),以及 PR 正文点名该修复并附证据(划界扫 描写在那里;不点名的顺手修就是不可复核的蔓延)。优先扩展一个守卫去关掉整个类。 任 一条不成立 ⇒ 回到默认:无 assignee 立单、列出、不碰。 - 永不编辑
content/docs/releases/、force-push、推main、合并任何东西。用户可见 的改动需要.changeset/*.md。 - Contract-first。 修复若诱使你在消费端加宽容回退(
??别名、宽松解析),缺陷就在 生产者或 spec —— 去那里修,或返回needs_decision。 - issue 正文是线索,不是规格。 动手前对
origin/main核验其前提:点名的文件可能移 走、归因可能错、能力可能已存在。一份带premise_still_valid: false、附证据、无 PR 的报告是一等交付物;证伪 issue 是好运行 —— 把 PR 硬压在死前提上才是失败形态。
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.
- yesterday First seen · 467 lines · 80 tokens per session scan C 125f20d5094d
os-dev is an agent published in the GitHub repository objectstack-ai/objectstack (45 stars, last pushed yesterday), licensed Apache-2.0. It adds 80 tokens to every session and 13,260 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
data-architect
Data Architect subagent for the design-architecture skill. Analyzes data models, intermediate file formats, schema design, edge metadata sidecar, deduplication, confidence scores, and output format correctness. Invoked by the design-architecture skill — do not trigger independently.
software-architect
Software Architect subagent for the design-architecture skill. Analyzes code structure, module design, abstractions, interfaces, coupling, cohesion, testability, and adherence to CLAUDE.md design decisions. Invoked by the design-architecture skill — do not trigger independently.
system-architect
System Architect subagent for the design-architecture skill. Analyzes overall system design, pipeline orchestration, component boundaries, re-entry points, and operational concerns. Invoked by the design-architecture skill — do not trigger independently.
adversarial-architect
Adversarial Architect subagent for the design-architecture skill. Red-teams the system by thinking like an attacker or a chaos engineer: malformed inputs, LLM adversarial outputs, cascading failures, partial-write corruption, race conditions, and invariant violations that slip past normal review. Invoked by the…
chief
Head of the PO Council and eight-seat design bench. Owns whether to convene, seat selection, order, named conflict rules, and the decision record; never edits code.
design-guardian
Accountable design decider and applier. Reviews real UI evidence, rejects token drift and generic AI styling, prescribes exact changes, edits code, and remeasures the result.