Agent skill

Summary

by devcodex-labs in devcodex-labs/devcodex

写入会话摘要到记忆日文件。区别于 memory Skill(会话记录读写)。任务结束前与 memory Skill 配合完成记忆持久化。

AGPL-3.0Auto-check passed

Install Summary

skills CLI
$ npx skills add devcodex-labs/devcodex --skill summary -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install devcodex-labs/devcodex summary --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/devcodex-labs/devcodex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/content/skills/summary .claude/skills/summary && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
summary
GitHub stars
439
Token cost
~491 tokens
SKILL.md length
132 words
Files
2
Skills in repo
70
Repo updated
First seen
Licence
AGPL-3.0

At a glance

写入会话摘要到记忆日文件。区别于 memory Skill(会话记录读写)。任务结束前与 memory Skill 配合完成记忆持久化。

  • SKILL.md covers 写入流程, 格式选择, 会话字段 and Token 防护写入, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Summary is an agent skill from devcodex-labs/devcodex. 写入会话摘要到记忆日文件。区别于 memory Skill(会话记录读写)。任务结束前与 memory Skill 配合完成记忆持久化。

Its SKILL.md is about 490 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `intent.json`).

The repository describes itself as: Intent-driven AI coding workflow runtime for consistent context, skills, approvals, validation, and handoffs across six AI coding hosts. The licence is AGPL-3.0.

Example prompts

  • “/summary”

What it can do on your machine

Read from SKILL.md and the folder at commit 1dd4525. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Summary loads about 491 tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 132 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
When it runs · the whole SKILL.md, loaded when a task matches
~491

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from devcodex-labs/devcodex at commit 1dd4525, republished under its AGPL-3.0 licence (© devcodex-labs). 132 words, ~491 tokens.

Download SKILL.mdSave it as .claude/skills/summary/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
summary
description
写入会话摘要到记忆日文件。区别于 memory Skill(会话记录读写)。任务结束前与 memory Skill 配合完成记忆持久化。

写入流程

<!-- devcodex:include shared/memory/active-root-layout.md -->
步骤动作
1确定日期(YYYYMMDD)
2定位文件:<active-root>/.memory/clients/<agent>/tasks/YYYYMMDD.md
3判断文件状态(不存在→创建;已存在→追加)
4确定会话编号(## 会话 01 起递增,两位数,按文件内容确定)
5写入初始段落(时间 + 意图 + 状态 🔄 + 摘要占位)
6后续更新(持续追加对话记录/报告路径/决策)

格式选择

场景格式
chat / 简单 analyze紧凑
audit(多轮)紧凑
dev/fix(≤2 文件变更)紧凑
dev/fix(≥3 文件变更)完整
多任务会话(≥3 任务)完整

首次写入可用紧凑格式,复杂度超出后升级(追加缺失字段,不重写已有内容)

会话字段

必填
字段说明
🎯 任务摘要本次任务的核心目标和意图
状态🔄 进行中 / ✅ 已完成(单独成行,供 resume 检测使用)
📨 对话记录四列表格:`轮次
按需(有内容时写入)
字段说明
📄 关联报告报告文件路径表格(含链接)
💡 关键决策本次会话中产生的重要决策
⚠️ 待跟进未完成事项或下次需要继续的内容
📦 编码检查点编码任务且变更 ≥3 文件时
🧭 HostCapabilityRoutingRef命中时只记录 instructionRefId / decisionId / authority / digestStrength / portableDecision / nativeStatus / fallbackReason,不复制原文或 catalog

Token 防护写入

配合 01-common.instructions.md C08 约束。

C08 阶段动作
🟡 关注区(>10 轮)在摘要中记录当前轮次
🟡 预警(>13 轮)写入编码检查点(📦 字段)
🔴 防护(>15 轮)立即写入完整记忆(所有字段填充到最新状态)
🔴 硬性暂停(≥15 轮 + ≥5 文件)必须先完成记忆持久化再继续

约束

  • 🔴 禁止询问用户"是否需要写入记忆"(C05/S05 强制自动写入)
  • 使用增量编辑追加,禁止覆盖已有内容(C06/S04)
  • 禁止使用 PowerShell Set-Content 等终端命令修改 .md 文件(C09)
  • HostCapabilityRoutingRef 只进入 daily/需求级记忆;Agent SUMMARY.md 仍是纯索引。compat/none 或 readback 未验证的 instruction authority 不得被摘要升级为跨轮 mutation 授权。

模板引用

产出物模板
会话段落(紧凑/完整)prompts/memory-session.prompt.md

© devcodex-labs, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in content/skills/summary of devcodex-labs/devcodex.

  • SKILL.md
  • intent.json

Open the folder on GitHubat commit 1dd4525

Compare with similar skills

Summary next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Summary compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Summary this skilldevcodex-labs/devcodex439—~491Automated safety check: PassAGPL-3.0
Speak Summarygithub/awesome-copilot40k—~1.6kAutomated safety check: PassMIT
Cost Summaryruvnet/ruflo74k—~594Automated safety check: NotesMIT
Stakeholder Summaryanthropics/claude-for-legal9.6k2 repos~3.3kAutomated safety check: PassApache-2.0
Investigation Summaryanthropics/claude-for-legal9.6k2 repos~326Automated safety check: PassApache-2.0
Deal Team Summaryanthropics/claude-for-legal9.6k3 repos~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Speak Summary

    github/awesome-copilot

    Official

    Convert text, markdown, or a summary produced by another skill into a listenable MP3 using local CPU-only neural text-to-speech.

    40k GitHub stars~1.6k tokensUpdated today
    Media & CreativeAuto-check passed
  • Cost Summary

    ruvnet/ruflo

    Single-shot programmatic dump of all cost data — total spend, per-tier, top session, budget status, federation aggregate.

    74k GitHub stars~594 tokensUpdated today
    Auto-check: notes
  • Stakeholder Summary

    anthropics/claude-for-legal

    Official

    Translates a contract review into a summary the business stakeholder will actually read.

    9.6k GitHub starsUsed in 2 repos~3.3k tokens
    Legal & ComplianceAuto-check passed
  • Investigation Summary

    anthropics/claude-for-legal

    Official

    Draft an audience-specific summary from the privileged investigation memo — HR, leadership, or outside counsel versions.

    9.6k GitHub starsUsed in 2 repos~326 tokens
    Auto-check passed
  • Deal Team Summary

    anthropics/claude-for-legal

    Official

    Aggregate diligence findings into a deal team briefing at the right altitude for the audience — exec summary for leadership, working summary for the team.

    9.6k GitHub starsUsed in 3 repos~1.3k tokens
    Business, Finance & HRAuto-check passed
  • Trailmark Summary

    trailofbits/skills

    Official

    Runs a Trailmark summary analysis on a codebase. An agent skill from trailofbits/skills.

    7.4k GitHub stars~926 tokensUpdated 2 days ago
    Auto-check: notes

More from devcodex-labs/devcodex

All 70 skills in this repo
  • Accessibility I18n

    devcodex-labs/devcodex

    无障碍与国际化专家 Owner — 当任务涉及可访问性、键盘操作、焦点、屏幕阅读器、ARIA、语言地区、本地化、RTL、翻译资源、用户可见文案或多语言文档时使用;要求把包容性体验和本地化验证绑定到真实用户路径。

    439 GitHub stars~718 tokensUpdated 23 days ago
    Auto-check passed
  • AI Agent System Architecture

    devcodex-labs/devcodex

    AI Agent 系统架构专家 Owner — 当任务涉及 Agent 路由、工具调用、上下文管理、记忆、状态机、权限、人机协作、可观测性、回放验证或模型辅助治理时使用;要求把 Agent 行为设计成可解释、可恢复、可审计。

    439 GitHub stars~2.4k tokensUpdated 23 days ago
    Auto-check passed
  • API Contract Architecture

    devcodex-labs/devcodex

    API 契约架构专家 Owner — 当任务涉及 public API、HTTP/SDK/CLI 契约、版本兼容、错误模型、分页过滤、幂等、Schema、类型、迁移或消费者影响时使用;要求先冻结消费者契约,再设计实现与验证。

    439 GitHub stars~865 tokensUpdated 23 days ago
    Auto-check passed
  • Architecture Design

    devcodex-labs/devcodex

    架构设计文档编排 Owner — 当用户要求架构设计、系统设计、技术架构或可指导开发、Review 与任务拆分的完整方案时使用;要求从业务流程反推节点、状态、数据、一致性、异常补偿、ADR 与实施任务。

    439 GitHub stars~1.1k tokensUpdated 23 days ago
    Auto-check passed
  • Audit Common

    devcodex-labs/devcodex

    审查公共维度 G0~G5 + Profile Freshness Check — 所有 audit 子类型必先执行的基础维度层

    439 GitHub stars~4.1k tokensUpdated 23 days ago
    Auto-check passed
  • Audit Session

    devcodex-labs/devcodex

    审计工作流的跨会话状态机 — 在 <audit-root/.audit-state/<session-id.json 持久化轮次/发现项/收敛状态,支持 Token 中断后精准恢复

    439 GitHub stars~1.8k tokensUpdated 23 days ago
    Auto-check passed

Questions about Summary

What does Summary do?

写入会话摘要到记忆日文件。区别于 memory Skill(会话记录读写)。任务结束前与 memory Skill 配合完成记忆持久化。. Summary is an agent skill from devcodex-labs/devcodex.

How do I install Summary in Claude Code?

Run `npx skills add devcodex-labs/devcodex --skill summary -a claude-code`. Or copy the skill folder (content/skills/summary in devcodex-labs/devcodex) into .claude/skills/summary in your project. Claude Code loads it when a task matches its description.

How do I install Summary in Codex?

Run `npx skills add devcodex-labs/devcodex --skill summary -a codex`. Or copy the skill folder (content/skills/summary in devcodex-labs/devcodex) into .agents/skills/summary in your project. Codex loads it when a task matches its description.

Can I use Summary in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add devcodex-labs/devcodex --skill summary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/summary, .gemini/skills/summary, .github/skills/summary and .opencode/skills/summary in your project.

What does Summary need to run?

SKILL.md names no scripts, command-line tools or credentials: Summary is instructions for the agent only.

Does Summary access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Summary safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Summary use?

Summary is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Summary use?

About 491 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Summary?

Skills that share tags, products or a category with Summary: Speak Summary (github/awesome-copilot, 40k stars), Cost Summary (ruvnet/ruflo, 74k stars), Stakeholder Summary (anthropics/claude-for-legal, 9.6k stars) and Investigation Summary (anthropics/claude-for-legal, 9.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Summary?

devcodex-labs (a GitHub organization) maintains it in devcodex-labs/devcodex, which has 439 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on September 17, 2026.

Source: devcodex-labs/devcodex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.