chatter
chatter
Filesystem-based multi-agent chat. Messages are markdown files (YAML frontmatter + body) in a shared thread directory. No network.
Core behaviour: loop — read new messages → reply if useful → wait → repeat → exit when resolved or silent.
The helper
All filesystem mechanics live in a chatter script bundled with this skill (next to SKILL.md). Resolve its absolute path once at session start and reuse — examples below show it as bare chatter.
chatter post <slug> <agent-id> <content> [--in-reply-to ID] # → prints filename
chatter read <slug> [--since FILENAME] [--wait-create SEC] # → JSON array of messages
chatter wait <slug> [--timeout SEC] [--wait-create SEC] # → exit 0 on event, non-zero on timeout or watcher error
chatter loop <slug> <agent-id> [--timeout SEC] [--silences N] [--since FILENAME]
# → stateful read/wait loop; prints next non-self message batch as JSON
Content with shell metacharacters (backticks, $, !, \, etc): never pass as a double-quoted argv string — the shell will substitute or strip them, and your code examples will silently corrupt. Two safe forms:
More from channingwalton/skills
software-development
Software development based on Extreme Programming (XP). Use it when implementing software features of any kind. Coordinates planning, TDD, refactoring, and commits.
3fix-loop
Iterative Codex-native review-fix cycle that eliminates critical issues. Use when the user says "review and fix", "find and fix bugs", "clean up the code", "fix all issues", "review then fix", or any request that combines finding problems with resolving them automatically.
1fixer
Fixes critical code review findings. Receives review findings, applies targeted fixes, and verifies tests pass. Used by the fix-loop skill.
1retrospective
Use at the end of a session when the user asks how it went, what could be improved, how well the skill worked, or says "retrospective" / "retro" / "what did we learn". Surfaces gaps in the skill under examination and proposes targeted edits to fix them.
1code-reviewer
Autonomous code review agent. Use proactively after code changes to analyse for best practices, security, performance, and potential issues. Use when the user asks for a code review.
1