recap

v0.1.0

Reconstruct one exact coding-agent session with Recall, git, and complete evidence accounting.

CodexClaude Code1 Skill

By Miguel RiosLicense: MIT61 GitHub starsUpdated 12 hours ago

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Sep 23, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install recap for Codex and Claude Code

Installs for the current user

codex plugin marketplace add Parcha-ai/parcha-skills
codex plugin marketplace upgrade unc-skills
codex plugin add recap@unc-skills

Paste and run these commands in a terminal with Codex. They add and refresh the unc-skills catalog, then install this plugin.

Compatibility: the page URL and API slug “recap-2” remain stable.

Codex: recap-2@agent-plugin-marketplace → recap@unc-skills

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/Parcha-ai/parcha-skills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is recap/.

Plugin files

recap/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/recap/SKILL.md

Included Skills1

recapskills/recap/SKILL.md

Reconstruct what a Claude Code or Codex agent actually did during one exact session, including goals, decisions, actions, file and git changes, tests, failures, recoveries, final state, and open work. Use when the user says "/recap", "recap this session", "what did this agent do", "give me the full handoff", or asks for an evidence-backed account of a long-running coding-agent session. Use Recall for prior-session discovery; use Recap after a session is identified. Never use it to expose hidden reasoning or to infer unobserved actions.

Plugin manifests2

recap/.codex-plugin/plugin.json

{
  "name": "recap",
  "version": "0.1.0",
  "description": "Reconstruct one exact coding-agent session with Recall, git, and complete evidence accounting.",
  "author": {
    "name": "Miguel Rios",
    "url": "https://github.com/miguelrios"
  },
  "homepage": "https://github.com/miguelrios/unc-skills/tree/main/recap",
  "repository": "https://github.com/miguelrios/unc-skills/tree/main/recap",
  "license": "MIT",
  "keywords": [
    "session-recap",
    "evidence",
    "handoff",
    "recall"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Recap",
    "shortDescription": "Explain one agent session end to end",
    "longDescription": "Reconstruct goals, decisions, actions, git state, tests, failures, final state, and open work from one exact Claude Code or Codex session boundary.",
    "developerName": "Miguel Rios",
    "category": "Productivity",
    "capabilities": [
      "Read"
    ],
    "websiteURL": "https://github.com/miguelrios/unc-skills/tree/main/recap",
    "defaultPrompt": [
      "Recap this session with evidence and exact coverage."
    ]
  }
}

recap/.claude-plugin/plugin.json

{
  "name": "recap",
  "version": "0.1.0",
  "description": "Evidence-backed end-to-end comprehension of one exact coding-agent session.",
  "author": {
    "name": "Miguel Rios",
    "url": "https://github.com/miguelrios"
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[recap on Agent Plugins Marketplace](https://pluginsmp.com/plugins/recap-2)