Checkpoint durable outcomes

SkillDocs & knowledge

Checkpoint durable decisions, fixes, constraints, results, and open next steps from the current Codex task into scoped Waggle project memory.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Checkpoint durable outcomes skill

What this skill tells your AI

The instructions your AI receives, as published by hashgraph-online/awesome-codex-plugins in plugins/Abhigyan-Shekhar/Waggle-mcp/skills/waggle-checkpoint/SKILL.md and read by ahel’s review.

  1. Review the current task and select only durable outcomes: decisions and rationale, verified fixes and causes, stable constraints, failed approaches worth avoiding, measured results, unresolved problems, and concrete next steps.
  2. Exclude greetings, raw command logs, speculative thoughts, secrets, duplicate facts, and details easily recovered from the current code unless their historical meaning matters.
  3. Determine the stable project scope: prefer the credential-free Git remote identity, otherwise the canonical absolute Git root or workspace path.
  4. Draft a compact checkpoint summary. Call observe_conversation with the user's checkpoint request as user_message, the summary as assistant_response, and the stable project, agent_id: "codex", and current session identifier when available.
  5. Report what categories were checkpointed and any non-fatal extraction errors. If there is nothing durable, say so and skip the write.

This is the Codex skill equivalent of /waggle-checkpoint; invoke it as $waggle-checkpoint.

Signals

GitHub stars
1k
Forks
278
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
waggle-checkpoint
Source
github.com/hashgraph-online/awesome-codex-plugins