← 返回 Skills 市场
tommot2

Context Brief

作者 TommoT2 · GitHub ↗ · v3.0.0 · MIT-0
cross-platform ✓ 安全检测通过
270
总下载
0
收藏
0
当前安装
16
版本数
在 OpenClaw 中安装
/install context-brief
功能描述
Persistent context survival for OpenClaw. Writes file-based anchors to memory/anchors/ to preserve critical context across sessions. Reads MEMORY.md and dail...
使用说明 (SKILL.md)

Context Brief v3.0

Install: clawhub install context-brief

Persistent context survival. Captures what matters before it's lost — and restores it when needed.

Writes ONLY to memory/anchors/. Reads MEMORY.md and daily logs — never modifies them.

Language

Detect from the user's message language. Default: English.

How It Works

Three levels of action, based on user request or trigger:

Level 1 — Context Note (1-2 unsaved items, low risk)

  • Append a brief note to your response, no file writes
  • Example: Unsaved context: [decision X pending, path Y important]

Level 2 — Anchor (3+ unsaved items OR user says "save context")

  • Write anchor file to memory/anchors/
  • Show summary to user after saving
  • Anchor contains task state, decisions, pending items — never credentials or secrets

Level 3 — Deep Anchor (user explicitly requests "save context deep" or "context check")

  • Full anchor with all categories
  • User gets the summary

Triggering

Anchors are written when the user explicitly asks ("save context", "context check", "hva husker du", "preserve context") or when resuming after time away.

Do NOT auto-save without user request. Level 2+ requires user initiation or explicit consent.

Write Permissions

File Read Write
memory/anchors/*.md ✅ — Only location this skill writes to
memory/YYYY-MM-DD.md ❌ — Never modified
MEMORY.md ❌ — Recommend changes to user
HEARTBEAT.md ❌ — Read only

Anchor File Format

Write to memory/anchors/YYYY-MM-DDTHH-mm.md:

# Anchor — YYYY-MM-DDTHH:mm+ZZ:ZZ

## Active State
- Task: [what we're doing]
- Status: [in progress / blocked / awaiting]

## Decisions
- [thing] -> [chosen option] (reason)

## Pending
- [ ] [next action with enough context to execute]

## Key Paths
- [path]: [what it is]

Rules:

  • Create memory/anchors/ if it doesn't exist
  • ISO 8601 timestamps
  • Max 20 lines — prioritize ruthlessly
  • REDACT secrets — strip any line containing: password, token, api_key, secret, bearer, private_key, or credential patterns
  • One anchor per checkpoint — never append to old anchors

After Writing

Show user (in their language):

Context anchored (N items) → memory/anchors/YYYY-MM-DDTHH-mm.md

Recovery — On Resume

When resuming or after compaction:

  1. Check memory/anchors/ for recent files (last 48h)
  2. If anchor found and items are missing from conversation:
    Restored from anchor: [brief list of items]
    Continuing: [last active task]
    
  3. If no anchor and context feels lost, ask the user what they were working on.

What This Skill Does NOT Do

  • Does NOT modify MEMORY.md, HEARTBEAT.md, or daily logs
  • Does NOT auto-save without user request or consent
  • Does NOT store credentials or secrets
  • Does NOT restore silently — always informs user
  • Does NOT create files outside memory/anchors/

Guidelines for Agent

  1. Wait for user trigger — "save context", "context check", or resume
  2. Keep it short — 20 lines max per anchor
  3. Redact secrets aggressively — strip any sensitive patterns
  4. Inform on restore — never restore silently
  5. Only write to memory/anchors/ — nowhere else
  6. One anchor per checkpoint — new file each time
  7. Language follows user — anchor content in the language being used
  8. Timestamp everything — ISO 8601

More by TommoT2

  • cross-check — Auto-detect and verify assumptions in your responses
  • setup-doctor — Diagnose and fix OpenClaw setup issues
  • locale-dates — Format dates/times for any locale

Install the full suite:

clawhub install context-brief cross-check setup-doctor locale-dates
安全使用建议
This skill appears coherent: it only needs to read memory files and write compact anchor files under memory/anchors/. Before installing, confirm you trust the skill author (source is unknown). Be aware it will create files in your workspace (memory/anchors/) when triggered; check or back up that folder if you care about disk contents. The redaction rule is superficial (line-based patterns) and can miss secrets embedded inline—avoid relying solely on the skill to remove credentials. Also clarify how 'resume' triggers work in your agent environment so you know when anchors might be created automatically. If you need stronger guarantees, request explicit, auditable safeguards (concrete log paths, stricter redaction, or a review of actual implementation) before enabling this skill in sensitive contexts.
能力评估
Purpose & Capability
Name/description (context persistence) aligns with instructions: reads MEMORY.md and daily logs and writes concise anchors to memory/anchors/. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
Instructions restrict writes to memory/anchors/ and require explicit user trigger for Level 2+, which matches the purpose. However 'daily logs' path is not concretely specified, redaction is only line-based (may miss inline secrets), and 'resume' triggers could cause writes when the agent autonomously regains context—these behaviors are vaguely defined and rely on the agent following the prose.
Install Mechanism
No install spec and no code files (instruction-only) — lowest install risk. The README mentions a 'clawhub install' command but there is no install artifact; nothing will be downloaded or written by an installer unless the platform executes that command separately.
Credentials
No environment variables, credentials, or external service access are requested. File read/write targets declared are proportional to purpose.
Persistence & Privilege
always:false and user-invocable:true are appropriate. Autonomous invocation is allowed by platform default; the SKILL.md forbids auto-saving without user consent but resumes and implicit triggers are permitted—this could lead to file writes without an explicit 'save context' phrase depending on how 'resume' is implemented.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install context-brief
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /context-brief 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.0.0
Fixed contradiction: daily logs are now read-only, never modified. Auto-save removed — anchors only on user request. Declared MEMORY.md and HEARTBEAT.md as config paths.
v2.1.1
Clarified auto-save scope (user's own workspace only), removed compaction detection, added group chat safety note.
v2.1.0
Auto-save anchors without confirmation, 3-level detection (note/anchor/deep), context notes for low-risk, simplified 2-step write, reduced recovery reads, clear write-permission table.
v2.0.1
Security fixes: never modify HEARTBEAT.md/MEMORY.md (read-only), user confirmation before proactive saves, inform on restore (never silent), secret redaction rules added.
v2.0.0
Complete rewrite: file-based persistent anchors, MEMORY.md integration, heartbeat support, recovery protocol, cross-session survival. Replaces stateless v1.x.
v1.8.2
Install command now inline for visibility
v1.8.1
Added standalone install command
v1.8.0
Repositioned from compaction helper to context preservation specialist. Added 4-tier priority system (must/should/nice/discard). Added Context Anchor protocol for pre-compaction survival. Added post-compaction recovery guidance. Removed self-promotion section.
v1.7.0
Security: removed final USER.md mention.
v1.6.0
Security: removed negative USER.md reference from documentation.
v1.5.0
Security v3: Made completely stateless. Removed ALL file I/O — no USER.md, no memory files, no write/read operations. Context briefs are session-only. No credential access.
v1.4.0
Security: replaced npx clawhub@latest with clawhub install.
v1.3.0
Added cross-promotion: recommends setup-doctor, locale-dates, tommo-skill-guard. Added starter pack install command.
v1.2.0
SECURITY FIX: Removed instruction to persist API keys and credentials. Added explicit redaction rules — never store raw secrets, tokens, or passwords. Addresses ClawHub security flag.
v1.1.0
Optimized description with SEO keywords, expanded trigger phrases, MEMORY.md integration mention
v1.0.0
Initial release: context health monitoring, smart compaction preparation, proactive memory archiving, multi-language output (no/en), locale-dates and setup-doctor synergy with cross-skill recommendations and preference sync.
元数据
Slug context-brief
版本 3.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 16
常见问题

Context Brief 是什么?

Persistent context survival for OpenClaw. Writes file-based anchors to memory/anchors/ to preserve critical context across sessions. Reads MEMORY.md and dail... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 270 次。

如何安装 Context Brief?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install context-brief」即可一键安装,无需额外配置。

Context Brief 是免费的吗?

是的,Context Brief 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Context Brief 支持哪些平台?

Context Brief 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Context Brief?

由 TommoT2(@tommot2)开发并维护,当前版本 v3.0.0。

💬 留言讨论