First subagent gets a horizontal 60/40 split (main left, agent right).
Subsequent subagents split vertically within the right column so they
stack. rightColumnPanes tracks right-column pane order so each new
split targets the last pane in the stack.
- plugins/tmux-panes.ts: opencode plugin that hooks into session.created/
session.deleted events to spawn a tmux pane per subagent running
'opencode attach', giving live visual TUI for each background agent
- opencode.jsonc: load the local plugin alongside @tarquinen/opencode-dcp
- skills/tmux-session/SKILL.md: teach agents to manage persistent tmux
sessions (dev servers, watchers, worktree windows) with oc- naming
- c.fish / cc.fish: auto-start a tmux session when invoked outside tmux
so the visual panes plugin can always activate
Add basic-memory as a global cross-project knowledge store alongside
the existing per-project .memory/ system. Agents can now persist
reusable patterns, conventions, and lessons learned across all projects
via MCP tools (write_note, search_notes, build_context).
Changes:
- opencode.jsonc: add basic-memory MCP server config
- AGENTS.md: rewrite Project Memory section for dual system with
routing table (global vs per-project)
- agents/lead.md: integrate basic-memory into phase transitions,
CONSULT, PHASE-WRAP, escalation, and knowledge freshness
- agents/sme.md: dual caching strategy (basic-memory for cross-project
guidance, .memory/ for project-specific)
AGENTS.md is now the canonical instruction file, with CLAUDE.md,
.cursorrules, and .github/copilot-instructions.md as symlinks to it.
This is simpler and more intuitive - the main file is at the root,
not buried in .github/.
Updated all references across agents, commands, skills, and .memory/.
Add three new sections to AGENTS.md addressing workflow gaps observed in
a session where 6 features were implemented but none were functionally
tested — only static analysis (type checks, linting) was used, resulting
in broken features shipped as 'done'.
New rules:
- Functional Verification: features must be end-to-end tested before
completion; static analysis alone is explicitly insufficient
- Mandatory Quality Pipeline: every feature gets reviewer + tester passes;
no batch validation; quality over quantity under time pressure
- Requirement Understanding Verification: verify understanding before
implementing features with implicit expectations or domain concepts
Also simplifies tester bash permissions and adds plan write permission.
Replace 4 separate instruction files with 1 real file + symlinks:
- .github/copilot-instructions.md is the canonical instruction file
- CLAUDE.md and .cursorrules are symlinks to it
- AGENTS.md stays as global config (not a project instruction file)
This eliminates all sync/merge logic - changes propagate automatically.
Changes:
- AGENTS.md: rewrite Cross-Tool Instruction Files section for symlink convention
- librarian.md: simplify to maintain single instruction file + verify symlinks
- lead.md: simplify PHASE-WRAP and Documentation Completion Gate
- commands (init, bootstrap-memory, save-memory): update for symlink model
- doc-coverage skill: verify symlinks exist and point correctly
Expand librarian role to own cross-tool instruction file sync,
.memory/ file maintenance, and knowledge merge workflows. Lead
now proactively dispatches librarian in PHASE-WRAP and Documentation
Completion Gate instead of handling docs inline.
AGENTS.md, CLAUDE.md, copilot-instructions.md, and .cursorrules may
contain project knowledge added by other tools or people. Agents now
read these files at session start and merge new knowledge into
.memory/knowledge.md as the canonical source.
Remove the megamemory MCP knowledge graph and replace with plain
markdown files in .memory/ for tracking plans, research, knowledge,
and implementation state. This enables collaboration across people
and agentic coding tools (Claude Code, Copilot, Cursor, etc.).
Changes:
- Remove megamemory MCP from opencode.jsonc
- Delete tool/megamemory.ts and .megamemory/ database
- Rewrite all 25 config files to use .memory/ markdown files
- Add cross-tool instruction file awareness (AGENTS.md, CLAUDE.md,
copilot-instructions.md, .cursorrules)
- Update save-memory, bootstrap-memory, status commands for md workflow
- Update all agent files, skills, and commands consistently
Add 7 new sections to lead.md addressing failure patterns observed in
real session transcripts: exploration sharding for context-exhausted
explorers, environment probe protocol for infrastructure verification,
finding completion tracker to prevent silently dropped findings, targeted
re-review to avoid infinite review loops, tester capability routing to
match agent tools to task requirements, post-implementation sanity check
for coherence verification, and artifact hygiene for temp file cleanup.
