pantheon
01Plugin Claude Code
The Pantheon marketplace — tools for AI coding agents.
3 9d ago A
tokens not measured
original MIT
iris
02Plugin Claude Code
Cross-tool context bridge between Claude Code and Codex. Logs your conversation and exposes it to the other tool so you can hand off plans, share context, and pick up where the other tool left off.
3 9d ago A
tokens not measured
original MIT
SessionStart
03Hook Claude Code
Runs when a session starts, executing session-start.sh. From gsaranti/pantheon.
3 9d ago A
tokens not measured
copy · 63% MIT
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing append-chat.sh. From gsaranti/pantheon.
3 9d ago A
tokens not measured
original MIT
Stop
05Hook Claude Code
Runs when the agent finishes a response, executing append-chat.sh. From gsaranti/pantheon.
3 9d ago A
tokens not measured
original MIT
iris-off
06Skill Claude CodeCodex
Pause Iris conversation capture for this project. Sets ison to false in .iris-config.yaml so the hooks no-op until you run /iris-on. Existing chat logs and last-response files are preserved; /iris-sync and /iris-relay still work for reading what's already on disk.
3 9d ago A 60 tokens
original MIT
iris-on
07Skill Claude CodeCodex
Enable Iris conversation capture for this project. Sets ison to true in .iris-config.yaml (creating the file if it doesn't exist) so the hooks fire normally on the next turn.
3 9d ago A 40 tokens
original MIT
iris-relay
08Skill Claude CodeCodex
Execute a plan that Codex produced. Reads the last Codex response from disk and treats it as a plan to implement. Use when the user wants Claude Code to pick up where Codex left off.
3 9d ago A 45 tokens
original MIT
iris-sync
09Skill Claude CodeCodex
Summarize what the user and Codex have been working on. Reads the Codex chat log from disk and returns a brief synthesis of the current state, recent work, and open threads. Use when you need context on what Codex is doing or has done.
3 9d ago A 57 tokens
original MIT
Agent Claude Code
Investigate one question against the existing codebase. Returns an inline report; writes nothing.
3 9d ago A 24 tokens
original MIT
Agent Claude Code
Investigate one technical question against the open web; return findings inline.
3 9d ago A 21 tokens
original MIT
Agent Claude Code
Review one implementation diff against the description, plan, and scope report it was meant to satisfy. Return a verdict with per-criterion evidence.
3 9d ago A 34 tokens
original MIT
Skill Claude CodeCodex
Produce SYNTHESIS.md (final form) and BUILD.md (the ordered backlog of build items).
3 9d ago A 25 tokens
original MIT
Skill Claude CodeCodex
Implement a planned task. Closes with a scope report.
3 9d ago A 18 tokens
original MIT
metis-init
15Skill Claude CodeCodex
Finalize project-specific Metis setup. Thin wrapper around the plugin's init.sh — creates .metis/, populates .metis/config.yaml, splices a delimited block into CLAUDE.md, and writes a .metis/CURRENT.md stub.
3 9d ago A 56 tokens
original MIT
Skill Claude CodeCodex
Produce an implementation plan for a free-text task description. Plan stays in chat.
3 9d ago A 21 tokens
original MIT
Skill Claude CodeCodex
Read the docs corpus and produce SYNTHESIS.md, INDEX.md, CONTRADICTIONS.md, and QUESTIONS.md in .metis/.
3 9d ago A 32 tokens
original MIT
Skill Claude CodeCodex
Dispatch the metis-task-reviewer subagent to judge a diff against the task description and plan. Returns a verdict with per-criterion evidence.
3 9d ago A 34 tokens
original MIT
Skill Claude CodeCodex
Update .metis/CURRENT.md with the session handoff.
3 9d ago A 18 tokens
original MIT
Skill Claude CodeCodex
Rehydrate a fresh session from on-disk state.
3 9d ago A 16 tokens
original MIT
Skill Claude CodeCodex
Walk captured open items one at a time, resolving each into the relevant source doc.
3 9d ago A 24 tokens
original MIT