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-routergit 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-router)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-router"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-router.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 | $0.00042 | $0.02824 |
| Opus 5 | $0.00021 | $0.01412 |
| Sonnet 5 | $0.00008 | $0.00565 |
| Haiku 4.5 | $0.00004 | $0.00282 |
Grade A, and why
briefbound-router 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Briefbound Router
目标
Briefbound 对齐意图、选择 owner 并推进验证。结果明确时直接完成；结果或边界会改变时主动商量。约束用于防错，不替代判断。
决策核心
- “修复/添加/优化/删除/调整”提供执行许可；目标、写入面和验收清楚且无自然闸门时直接推进。
- 下游继承许可，切换 owner 不重问；仅范围扩大、高风险或真实取舍需确认。
HIGH：行动；MEDIUM：声明低风险假设后行动；LOW：probe/讨论；BLOCKED：只问不可约问题。- 输出用
SILENT / MICRO / ALIGN / FULL，默认最短；不展示内部账本。 - “继续/确认/按建议/按推荐来”先做
Continuation Health Check，仅继承仍完整的契约；缺结果/surface/evidence 或新增可见分叉就 probe/对齐。 - 声称刷新 skill 前必须重读本机
SKILL.md。
讨论式意图收敛
开发、规划或高影响审查前以 Alignment Value Gate / Alignment Completeness Gate 检查 Desired Result / Owning Surface / Acceptance Evidence / Highest-impact Fork。前三项缺失为 MISSING_CONTEXT：一次窄范围只读 probe，不索取本地可发现信息。存在多个实质结果为 PRODUCT_FORK：执行 One-Turn Alignment；否则行动。低置信度不得带着未确认的高影响假设写入。
PRODUCT_FORK 进入 ALIGNMENT_PENDING：只读 probe/Briefbound Router 对齐，不加载开发/planning owner、不写入。用户“按推荐”或纠正后进入 CALIBRATED，更新契约并重选/读取 owner，不重问已确认项。
- agent 先给具体建议，不让用户重写需求；一次集中提出 2-4 个高影响问题，说明建议、替代结果和误解风险。
- 主动暴露最可能造成误改的分叉；不得静默替用户决定产品行为，也不得询问本地证据已经回答的问题。
- 不强制套字段。对齐时用通俗话说明理解、依据、建议、替代结果和误解风险，末尾邀请回复“按建议”“按推荐”或直接纠错。
- 自然闸门：意图/范围变化、不可安全恢复的失败、高风险/破坏性/权限/迁移/发布、冲突或真实取舍。
开发中执行 Unexpected Issue Gate：新证据若改变契约行为、范围、数据/API、安全或验收，停止受影响写入，带证据/影响/推荐讨论，不得扩大范围或硬做；契约内可逆恢复则处理并简报，确认后更新再继续。
展示 ALIGN/FULL 或破坏性菜单时才读 references/output-forms.md。
Owner 与组合
扫描最多 3 个候选，选能直接产生下一证据的最具体 owner。内部 Route Contract：Owner / Mode / Next Output / Allowed Action / Success Evidence / Stop Condition；动作分 READ / WRITE / REMOTE_WRITE / DESTRUCTIVE。
- bug/失败测试：
briefbound-bug-review；PR/diff：briefbound-pr-review；整仓/架构：briefbound-project-review。 - UI/UX 与交互：
briefbound-ui-design；品牌视觉：briefbound-visual-design；生产前端：briefbound-frontend-engineering；界面审查：briefbound-ui-review；token/主题/组件治理：briefbound-design-system。 - 请求包含前端写入时，若最终界面尚未获用户确认，先读取
references/ui-preview-approval.md，判定PREVIEW_REQUIRED / PREVIEW_SKIPPED。PREVIEW_REQUIRED必须先交付隔离网页并等待用户APPROVED / REVISE / ABANDON；批准前不得修改正式 UI owning surface。 - 当前 diff 过度设计：
briefbound-simplification-review；整仓冗余治理：briefbound-simplification-audit。 - 开发中出现多职责巨型文件、难导航/测试或反复结构冲突：
briefbound-code-structure-guard；行数本身不触发拆分。 - AI/ML 研究：
briefbound-ai-research-loop；单条 metric lane：briefbound-score-loop；重要 claim：briefbound-research-rigor-review。 - 多会话协商：
briefbound-multi-agent-orchestration；单次冲突：briefbound-thread-coordination；自动本地集成：briefbound-autonomous-collaboration-loop；残留：briefbound-development-cleanup。 - 真实设计分叉：
briefbound-planning；无专项 owner 的评价：briefbound-evaluation。 - GitHub、浏览器、Figma、OpenAI 文档、图片和办公制品按需读
references/capability-routing.md。
What ships with it
9 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.
- agents/openai.yaml 375 B
- references/capability-routing.md 4.3 KB
- references/collaboration-discovery.md 1.7 KB
- references/github-skill-candidates.md 11 KB
- references/output-forms.md 2.9 KB
- references/review-test.md 2.6 KB
- references/routing-practice.md 9.2 KB
- references/runtime.md 4.1 KB
- references/ui-preview-approval.md 3.0 KB
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 · 115 lines · 42 tokens per session scan A 020c466ad39d
briefbound-router is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 25d ago), licensed MIT. It adds 42 tokens to every session and 2,824 once invoked, about $0.0002 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
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.
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
mcp-builder
A guide to building Model Context Protocol (MCP) servers, which let AI assistants use tools and read external data. It covers server structure, tool design, testing, and deployment in TypeScript and Python.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.