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 skills/ccdawn/codex-skills/briefbound-project-memorynpx skills add CCDawn/codex-skills --skill briefbound-project-memorygit 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-project-memory)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-project-memory"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-project-memory.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 | $0.00065 | $0.01189 |
| Opus 5 | $0.00032 | $0.00594 |
| Sonnet 5 | $0.00013 | $0.00238 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
briefbound-project-memory 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Briefbound Project Memory
目标
按需维护 .docs/project-memory/ 和 HTML 总览,并为同项目 Agent 提供不入 Git 的 live coordination registry。memory 只保存会改变未来行动的事实;普通开发不自动初始化、同步或渲染。
Briefbound task contract
- Context Boundary: 目标仓库、现有 memory、live registry、项目规则和需持久化的事实。
- Output Contract: READ/INIT/SYNC 结果、持久 delta、渲染/registry 验证和 Route Out。
- Allowed Action: 只操作 memory/dashboard 与协调工具;不修改业务代码或伪造 claim、进度和验证。
- Success Evidence: 来源可追溯,delta 写入正确 lane,索引/HTML/registry 一致且不覆盖并行改动。
- Stop Condition: 用户/规则未要求、事实源不明、ownership 冲突、脚本缺失、渲染失败或写入会覆盖他人状态。
- Route Out: 原任务 owner、
briefbound-autonomous-collaboration-loop、briefbound-thread-coordination、briefbound-completion-summary、briefbound-router或 BLOCKED。
统一调用契约
- 只处理 Briefbound task contract 范围;不匹配时回
briefbound-router或更具体 owner,复合任务不吞其他 owner。 - 用户可见内容默认中文;保留技术字面量;只报产出、证据与风险;Route Out 仅以 Briefbound task contract 为准,末行写
下一步建议: <一个具体动作>。
激活与模式
仅在以下任一成立时使用:用户/项目规则明确要求;已有 memory 是恢复所需事实源;跨会话决定/blocker/handoff 必须持久化;真实多 Agent 协作需要 registry。
READ:只读INDEX.md、profile.json和会改变判断的 lane,不加载全部历史。INIT:用户/规则要求且目录不存在时初始化。SYNC:只写本轮 durable delta,不记录完整对话、旁白或普通测试日志。
现有 .docs/project-memory 存在时先读规则和索引;无目录且未触发 INIT 时直接返回原 owner。
Memory 不接管执行循环。自动闭环由 briefbound-autonomous-collaboration-loop 持有,memory 只提供可恢复状态载体;当前动作和短期续接留在 Briefbound runtime。只有已确认决定、跨会话 blocker、正式 handoff 或会改变未来行动的验证结论才写入,不为每个 task、测试或 checkpoint 重写并渲染。
事实与结构
- 代码/Git/运行结果是实现事实源;memory 是恢复与决策投影,不能覆盖源事实。
lanes/*.json按稳定职责保存状态、决定、问题和 next step;memory.json只保留全局事实。INDEX.md与overview.html是投影,不作为 claim 或运行状态权威。- 绝对 worktree、thread id、secret 和敏感日志不进入 tracked dashboard。
首次初始化才读取 references/setup.md,运行 init_project_memory.py。已有结构使用 sync_project_memory.py、capture_note.py 和 render_overview.py;参数以脚本 --help 为准。capture_note.py 仅保存仍需调查的高价值线索。
并行协作
存在真实并行或 registry 已存在时使用 agent_coordination.py <project-root> status/join/update/claim/open/respond/resolve/pause/resume/complete。
live registry 位于 <git-common-dir>/briefbound/coordination/registry.json;非 Git 项目回退 ~/.codex/project-coordination/<project-id>/registry.json。它跨 worktree 共享、不入 Git,并使用文件锁、revision 和原子替换。
What ships with it
22 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 334 B
- bin/agent-html-memory-capture.js 918 B runs code
- bin/agent-html-memory-coordinate.js 921 B runs code
- bin/agent-html-memory-guard.js 922 B runs code
- bin/agent-html-memory-init.js 925 B runs code
- bin/agent-html-memory-sync.js 925 B runs code
- package.json 608 B
- references/AGENTS-snippet.md 1.7 KB
- references/html-design.md 4.4 KB
- references/setup.md 5.3 KB
- references/troubleshooting.md 5.3 KB
- scripts/agent_coordination.py 29 KB runs code
- scripts/agent_work_guard.py 130 B runs code
- scripts/capture_note.py 2.5 KB runs code
- scripts/coordination_model.py 42 KB runs code
- scripts/init_project_memory.py 4.4 KB runs code
- scripts/install_codex_memory.py 1.0 KB runs code
- scripts/memory_model.py 6.5 KB runs code
- scripts/profile_model.py 9.4 KB runs code
- scripts/render_overview.py 43 KB runs code
- scripts/sync_project_memory.py 8.4 KB runs code
- tests/test_agent_coordination.py 66 KB runs code
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.
- 5d ago First seen · 67 lines · 65 tokens per session scan A 7bb97d41464d
briefbound-project-memory is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 23d ago), licensed MIT. It adds 65 tokens to every session and 1,189 once invoked, about $0.0003 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
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。.
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
systematic-debugging
Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
context-engineering
项目级上下文工程框架:通过 PROJECT / REQUIREMENTS / ROADMAP / STATE 四层文档 为每个任务建立结构化上下文,控制 token 预算,防止上下文腐烂, 确保跨会话连续性。与 context-lifecycle 的 L0-L3 层互补。.