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 YangFan-Code-Star/context-dev --skill maintaingit clone --depth 1 https://github.com/YangFan-Code-Star/context-devWrote 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/yangfan-code-star/context-dev/maintain)<a href="https://agentmods.dev/skills/yangfan-code-star/context-dev/maintain"><img src="https://agentmods.dev/badge/skills/yangfan-code-star/context-dev/maintain/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/yangfan-code-star/context-dev/maintain"><img src="https://agentmods.dev/badge/skills/yangfan-code-star/context-dev/maintain.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 | $0.00100 | $0.00797 |
| Opus 5.5 | $0.00040 | $0.00319 |
| Sonnet 5.5 | $0.00020 | $0.00159 |
| Haiku 4.5 | $0.00010 | $0.00080 |
Grade A, and why
maintain 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 1mo 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.
What it actually says
维护上下文（轻量）
轻量项目没有 audit-context.mjs，但同样可以长期迭代：上下文量小，直接读文件核对就够了。四步，十分钟以内。
流程
- [ ] 1. 核对事实
- [ ] 2. 合并任务日志
- [ ] 3. 删过期内容
- [ ] 4. 更新当前状态
1. 核对事实
把 AGENTS.md 逐行对照真实仓库：
- 快速上手与验证命令：真的跑一遍，不是看一遍。
- 目录地图：对照实际顶层目录。
- 铁律：还成立吗？换掉的技术要删掉对应规则。
docs/plan.md：一句话、成功标准、口径还符合用户现在的意图吗？
发现不一致就改文件，不要迁就文件。
2. 合并任务日志
逐条处理 docs/log.md「待合并」下的条目。先问一句：模型本来就猜得到吗？ 猜得到就直接删。
- 稳定的事实、口径、决定 → 合并进
docs/plan.md或AGENTS.md，删掉日志条目。 - 只出现一次的纠正 / 流程 → 留在日志里，等第二次出现再晋升。
- 违反后果不可逆或不可发现的高风险规则 → 立即升级为
AGENTS.md铁律，删掉条目。 - 已确认但只属于一次性环境的坑 → 在日志里保留现象，不要升级成铁律。
3. 删过期内容
过期的规则比没有规则更糟。 优先删：换掉的技术对应的规则、已经写进代码结构不必再说的约定、当时怕出错但从没出过错的叮嘱、模型本来就知道的通用建议。
4. 更新当前状态
把 docs/plan.md「当前任务与下一步」更新到本次维护后的最新状态；AGENTS.md「当前状态」只写一行指针，细节留在 plan.md。
汇报
## 维护结果
- 已核对的命令 / 目录：<哪些，结果如何>
- 已合并：<日志条目> → <目标位置>
- 已删：<过期内容及原因>
- 需要你确认：<有分歧的条目>
新增内容放哪
| 内容性质 | 位置 |
|---|---|
| 每次对话都要遵守 | AGENTS.md 铁律 |
| 背景、口径、计划 | docs/plan.md |
| 决定、坑、待观察纠正 | docs/log.md |
| 重复性多步流程 | 新建 .agents/skills/<name>/SKILL.md，并登记进 AGENTS.md「可用技能」 |
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.
- 1mo ago First seen · 65 lines · 100 tokens per session scan A 0b0a3940d29c
maintain is a skill published in the GitHub repository YangFan-Code-Star/context-dev (2 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 797 once invoked, about $0.0004 per session on Opus 5.5. 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
openspec-bulk-archive-change
Archive multiple completed OpenSpec changes at once. Use when archiving several parallel changes. Also use for a plural archive request - "openspec bulk-archive", "opsx bulk-archive", "openspec archive all", or "openspec archive these changes".
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach. Also use when the user says "openspec new change" or "opsx new".
openspec-archive-change
Archive a completed OpenSpec change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete. Also use when the user says "openspec archive" or "opsx archive".
product-manager
A product-management guide covering work from discovering a need through launch and measurement. It includes tools such as PRDs, which describe a product requirement, and RICE, a method for ranking opportunities.
product-sprint-prioritizer
A product-planning skill that ranks a list of requests with frameworks such as RICE, a method that compares reach, impact, confidence, and effort. It can also organize work into iterations or Sprints, which are fixed periods for completing a selected group of tasks.