Context Capsule

Compresses older OpenClaw agent session history into a bounded, lane-change-aware context capsule — keeps recent messages verbatim, flags abandoned directions, quarantines injected instructions, and redacts secrets. Local, deterministic, any model.

23 stars 3 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Parad0x-Labs/openclaw-skills --skill context-capsule
Manual install
git clone --depth 1 https://github.com/Parad0x-Labs/openclaw-skills.git /tmp/openclaw-skills
mkdir -p ~/.claude/skills
cp -r /tmp/openclaw-skills/skills/context-capsule ~/.claude/skills/context-capsule

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Context Capsule

Compress older agent session history before it hits the LLM, so long chats stop
re-sending the full transcript every turn. It keeps the recent tail verbatim and
turns older history into a bounded extractive capsule with decisions, tasks,
errors, paths, links, questions, and durable facts. Works with any model —
Claude, GPT, Ollama, Mistral, LM Studio.

**What sets it apart:**

- **Lane-change aware.** When the session pivots ("replace X with Y", "forget X,
  use Y instead"), the capsule marks the abandoned direction as superseded and
  keeps the live one, so the model is steered away from a dropped plan. On the
  6-case pivot set in `test/supersession-bench.mjs` (5 pivots, 1 no-pivot
  control, 6 abandoned subjects) v1.7.0 strikes or omits 6 of 6 abandoned
  subjects and flags 0 live choices at budgets 700 and 1,400; `npm test` fails
  below 83% or on any wrongly flagged live choice. Pivots stated without an
  explicit cue are not detected.
- **High fidelity per token.** Distinctive signals — file paths, IDs, ports,
  URLs, commands, errors, decisions — are emitted as dense atoms. As of **v1.7.0**,
  a lone value (a bare port `5433`, an issue ref `#4821`, a version `v2.13.0`, an
  ISO date, a hyphenated code like `NEEDLE-ZX-7742`) is emitted as its **own** atom,
  so it survives compression even when its surrounding sentence loses the budget
  race (`test/value-survival.test.mjs`). On the public 109-message fixture in
Read the full skill on GitHub

Details

Skill name
context-capsule
Path
skills/context-capsule/SKILL.md
License
MIT
Repo updated
13 November 2026

FAQ

What does the Context Capsule skill do?

Compresses older OpenClaw agent session history into a bounded, lane-change-aware context capsule — keeps recent messages verbatim, flags abandoned directions, quarantines injected instructions, and redacts secrets. Local, deterministic, any model.

How do I install the Context Capsule skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Parad0x-Labs/openclaw-skills --skill context-capsule. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Context Capsule popular?

It lives in Parad0x-Labs/openclaw-skills, which has 23 GitHub stars and 3 forks.

Related skills

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.