Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Compact Handoff

ASecurity

Use during long tasks when evidence, state, and next actions must survive context compaction. Handles compaction judgment and handoff records only; no automatic hook behavior.

15 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentspythondebugging

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add AidALL/ghost-alice --skill compact-handoff --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Compact Handoff?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Compact Handoff
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aidall-compact-handoff/badge)](https://www.skillsdirectory.com/skills/aidall-compact-handoff)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: compact-handoff
description: "Use during long tasks when evidence, state, and next actions must survive context compaction. Handles compaction judgment and handoff records only; no automatic hook behavior."
compatibility:
  - "Python 3.11+ standard library"
---

# compact-handoff

compact-handoff preserves task continuity before or after context compaction. It does not trigger automatic compaction, add hooks, or create background summaries. It only defines the quality bar for a handoff that a human or future agent can safely resume.
## Contents

- [When To Use](#when-to-use)
- [Pre-Compaction Record](#pre-compaction-record)
- [Do Not Compact When](#do-not-compact-when)
- [Resume Procedure](#resume-procedure)
- [Validator Rules](#validator-rules)
- [Warnings](#warnings)


## When To Use

- Context is long enough that work state may be lost.
- Another session or agent must continue the implementation.
- Test results, changed files, remaining work, forbidden surfaces, or rollback paths need to survive compaction.

## Pre-Compaction Record

Write a short handoff with these fields, then validate it with `scripts/compact_handoff.py <handoff-file> --json`. If validation returns `status=fail`, fix the handoff before compacting.

```text
[compact-handoff]
- objective: <current objective>
- completed: <completed work>
- in-progress: <current item>
- next-step: <one next action>
- files-changed: <absolute paths>
- tests-run: <commands and results>
- forbidden-surface: <paths or actions not to touch>
- rollback: <nearest rollback path>
```

## Do Not Compact When

- A RED test is failing and the root cause is still unknown.
- A live configuration file is being edited without a rollback path.
- The next step is a user approval gate.
- Secret, token, credential, or private key text is exposed in the context.

## Resume Procedure

1. Read `objective`, `in-progress`, and `next-step` first.
2. Inspect the real diff for `files-changed` and compare it with the handoff.
3. If the most recent test failed, route into systematic-debugging.
4. Claim completion only after verification-before-completion runs again.

## Validator Rules

- All 8 required fields must exist.
- Secret-like values fail validation. The validator must not print raw values.
- Handoffs that touch live config such as `~/.claude/settings.json`, `~/.codex/hooks.json`, `~/.codex/config.toml`, or `~/.agents/skills/` need a concrete rollback path.
- `tests-run: not run` or `pending` produces a warning. That warning does not block compaction, but it blocks completion claims.

## Warnings

- Do not call `/compact` automatically.
- Do not use compact-handoff as a reason to create extra reports or plans.
- Do not use compaction to hide uncertainty.
- A handoff is a continuity artifact, not evidence that the work is complete.

Attribution

AidALLAidALL
View sourceMore from AidALL →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →