goal
01Plugin Claude Code
Persistent objective lifecycle for Claude Code: set a goal once, Claude pursues it across turns until it is verifiably done.
1 3mo ago A
tokens not measured
original MIT
1Stars on the repository
7Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
SessionStart
02Hook
Runs when a session starts, running bash. From pyyush/goal.
1 3mo ago A
tokens not measured
original MIT
Stop
03Hook
Runs when the agent finishes a response, running bash. From pyyush/goal.
1 3mo ago A
tokens not measured
original MIT
Notification
04Hook
Runs when the agent sends a notification, running bash. From pyyush/goal.
1 3mo ago A
tokens not measured
copy · 86% MIT
Hook
Runs when you submit a prompt, before the agent sees it, running bash. From pyyush/goal.
1 3mo ago A
tokens not measured
original MIT
goalframe
06Skill Claude CodeCodex
Turn a raw, vague, or oversized objective into a structured, verifiable goal spec BEFORE a /goal record is written. Always run this skill first whenever a user runs /goal , sets a durable multi-turn objective, or asks Claude to "keep working until" something is done. It produces the six things a goal needs to be…
1 3mo ago A 150 tokens
original MIT
overclaim
07Skill Claude CodeCodex
Evidence-discipline gate that prevents Claude from overstating progress or completion. Use this skill BEFORE marking a goal achieved, BEFORE writing any progress report, and BEFORE telling the user something is "done", "fixed", "working", "passing", or "complete". Always run it when a /goal is active and Claude is…
1 3mo ago A 129 tokens
original MIT
At most 3 mods per repository are shown here — the rest are on their repository pages: