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 CCDawn/codex-skills --skill briefbound-autonomous-collaboration-loopgit clone --depth 1 https://github.com/CCDawn/codex-skillsWrote 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/ccdawn/codex-skills/briefbound-autonomous-collaboration-loop)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-autonomous-collaboration-loop"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-autonomous-collaboration-loop/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/ccdawn/codex-skills/briefbound-autonomous-collaboration-loop"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-autonomous-collaboration-loop.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00074 | $0.02098 |
| Opus 5 | $0.00037 | $0.01049 |
| Sonnet 5 | $0.00015 | $0.00420 |
| Haiku 4.5 | $0.00007 | $0.00210 |
Grade A, and why
briefbound-autonomous-collaboration-loop 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Briefbound 自动协作开发闭环
目标
用户确认一次后，驱动同项目平级会话完成各自任务、恢复冲突、验证并合入本地 main。不创建主从团队或接管其他任务。
Briefbound task contract
- Context Boundary: 已对齐的共同目标、用户一次性授权、现有同项目 thread、各自任务/branch/worktree/scope、共享契约、目标
main和验证门。 - Output Contract: collaboration agreement、可接管状态、各任务交付证据、integration queue、本地
main验证、恢复与清理闭环。 - Allowed Action: 在授权范围内读取/发送 thread 消息、维护 registry、执行本地写入/提交/合入
main、验证和安全清理；新建会话、远程 push/PR merge/发布、破坏性或高风险动作仍需单独授权。 - Success Evidence: 每个原任务达到验收，目标
main包含预期交付，集成门通过，open coordination、恢复债务和已知开发残留清零。 - Stop Condition: 未获开启确认、共同目标或 target 不明、产品/安全/数据迁移取舍未决、需要远程授权、破坏性动作，或自动恢复连续失败。
- Route Out: 各 Agent 原 owner、
briefbound-multi-agent-orchestration、briefbound-thread-coordination、briefbound-pr-review、briefbound-development-cleanup、briefbound-project-memory、briefbound-router或 BLOCKED。
统一调用契约
- 用户可见内容默认中文；只报行动决定、blocker 和最终证据。Route Out 仅以 Briefbound task contract 为准；末行写
下一步建议: <一个具体动作>。 - 各 Agent 保留自己的任务、scope、branch 和完成责任；Loop Owner 只维护闭环，不成为其他任务的 owner。
- 开启后不在每个阶段、task、普通冲突或恢复动作后询问是否继续。
开启与授权
Briefbound Router 仅在非简单目标确有多会话协作价值时询问一次：“是否开启自动化协作开发闭环？”确认后持续授权联系现有会话、协商、安全开发、本地提交与 main 集成、验证和清理，直到完成、取消或自然闸门。
没有合适会话时，只询问一次是否创建。远程 push、PR 或破坏性操作不继承授权。
角色与持久状态
Loop Owner：维护状态、租约、outbox、恢复债务和完成门，不代写 peer 结论。Peer Owner：完成任务，提供 scope、依赖和MERGE_READY。Integration Owner：由任一合格 peer 在首个MERGE_READY出现后主动原子认领，维护当前队列、按依赖重验并合入main；claim 有效期间不启动新的无关实现任务，变忙时先转交队列。Recovery Dispatcher：任何活跃参与者在 Loop Owner 租约过期时可takeover，继承 outbox、恢复和集成义务，但不能继承或伪造 peer 的完成声明。
状态为 DISCOVER -> AGREEMENT -> RUNNING/NEGOTIATING -> MERGE_READY -> INTEGRATING -> INTEGRATED -> CLOSED。每个 peer 只记 Task / Scope / Branch or Worktree / Dependency / Checkpoint / Tests / Blocker / Resume Debt；优先 registry，跨会话恢复才用 memory。
自动循环
1. 发现与约定
只读最多 3 个相关 thread，确认收益、边界、契约、依赖和 Integration Target，用 briefbound-multi-agent-orchestration 建 agreement。Integration Owner 可等首个交付入队后认领；无收益则返回原 owner。
2. 并行推进
各 peer 继续非冲突任务，只在契约变化、依赖就绪、可行动证据、纠错、blocker 或 MERGE_READY 时通信；不轮询。消息默认只发差量：From/Task / Changed Fact / Action Impact / Evidence Pointer / Reply Needed；背景、方案和测试用指针，首次契约或安全语义才展开。
What ships with it
1 file 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 · 101 lines · 74 tokens per session scan A ff878446d4f7
briefbound-autonomous-collaboration-loop is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 26d ago), licensed MIT. It adds 74 tokens to every session and 2,098 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 2026-08-31.
Other skills, from other repositories
requirement-delivery
A workflow for turning a new software request into a small, working deliverable. It clarifies acceptance criteria, identifies boundaries, breaks work into demonstrable parts, and looks for existing code or tools to reuse.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
batch-all-issues
Resolve every open issue one at a time: fact-check each with web research, close the ones that need no action, and run the goal-pr skill to fix, review, and merge the ones that do — repeating until no actionable issues remain.
post-issue-comment
Post a reply comment on a GitHub issue in English with a natural, concise writing style, based on the intent passed as arguments.