Coniso

Coniso: context-isolated agent teams for Claude Code

by Palatine Labs · pronounced CON-ih-so (short for context isolation)

Call a role and it brings its team. Every agent works in a clean, small context, and a deterministic script handles the bookkeeping so no model has to.

Status: v1.2. The core is stable and in daily use. Expect sharp edges on uncommon setups. Please report them as issues.

Claude Code only. Coniso runs a local Python script, git worktrees and nested subagents, so it needs Claude Code: the terminal, an IDE extension, or the desktop app's Code tab. In claude.ai chat it installs but has nothing to run on. Cowork is untested.

---

The problem

Long Claude Code sessions on large codebases degrade in two predictable ways:

• Context bleed. One session accumulates file dumps, diffs, test logs and dead ends from every task it has touched. Later work is reasoned against that noise, instructions from early in the session get diluted, and quality drifts.
• Token waste. The same session re-reads all of that history on every turn. Ad hoc subagents help, but they usually hand raw output back up the chain, so the main context fills up anyway, just more slowly.

Coniso is built to reduce both, mostly through structure rather than prompting alone:

• Every subagent gets one packet in a fresh context and is told to return at most 12 lines. Detail (briefs, assignments, diffs, test logs, reports) lives in files under .coniso/, and agents are told to pass paths, not contents. That keeps raw output from climbing the hierarchy. It's a rule agents follow, not a limit the script enforces.
• A plain Python script, not an LLM, owns the bookkeeping: scheduling, dependency waves, sprint state, git worktrees, diffs, merges, plan validation and roadmap edits. No tokens are spent on graph math or rule checks a script can do.
• The main session is built to stay small for hours, and a sprint survives a restart ("director, continue").

Roles

The main session is always the top of the hierarchy. You call a role, and it brings the team it needs:

You call	Agent · default model	It brings	Use it for
Engineer (/coniso:engineer)	coniso:engineer · sonnet (haiku for mechanical, opus for hard)	itself: one worker, no worktree	a quick, well-defined task
Lead (/coniso:lead)	coniso:lead · sonnet (opus on opus tickets)	one ticket in its own git worktree: a solo engineer plus one reviewer for S/M tickets, a lead with 3–4 engineers for L tickets	one roadmap ticket or one described feature
Manager (/coniso:manager)	coniso:manager · opus	a track of teams and solo engineers, one dependency wave at a time	a roadmap phase or workstream
Review Lead (/coniso:review)	coniso:review-lead · opus	adversarial reviewers	verdicts on built tickets, or a sweep for defects over merged work
Director (/coniso:director)	the main session	everything above	a long session working through a block of your roadmap

Support roles, spawned by leaders, never by you:

• Reviewer (coniso:reviewer, and coniso:reviewer-lite for small diffs: patch tickets, delta re-reviews, haiku batches): adversarial review against the acceptance criteria, within a tool-call budget the script sizes from the diff. Every finding needs evidence. It also hunts for gamed tests: deleted or loosened tests, hard-coded expected values, TODOs claimed as done. Builders never judge their own work.
• Auditor (coniso:auditor): a model one tier cheaper than the leader it audits. It challenges judgment calls (model tier, packet size, ordering, scope) and review rulings. Every overrule is logged, so the retro shows whose routing is going wrong.
• Scout (coniso:scout): read-only recon of a codebase area or docs question, written to a short map file.

Specialties (builder, tester, ui, net, level, audio, docs, batch, artisan, synth) are scoped guidance injected into a generalist engineer. They aren't personas with lanes to get stuck in.

Install

Inside Claude Code:

/plugin marketplace add Palatine-Labs/coniso
/plugin install coniso@coniso

Or from your shell:

claude plugin marketplace add Palatine-Labs/coniso

claude plugin install coniso@coniso

Install it from one source only. A copy added from Anthropic's directory on claude.ai appears in Claude Code as coniso@synced; if you also install coniso@coniso, disable one of them.

Requirements

• Claude Code with plugin support. Nested subagents give full parallelism; without them, relay mode keeps sprints working with less (see below). Developed and tested on v2.1.292. Older 2.1.x releases may work but aren't tested.
• Python 3.8+ on PATH as python3, python or py -3. Standard library only.
• git: each ticket builds in its own worktree. For non-code work, init with --no-worktrees.
• Windows, macOS and Linux.

Experimental flags

None required. Coniso runs on Claude Code's defaults. Two existing values would break nesting, and Coniso offers to fix them (see Permissions):

• CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH below 3: fix sets it to 3.
• CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1: fix sets it to 0. Coniso uses its own hierarchy, not experimental agent teams.

If nested spawning isn't available at all, leaders switch to relay mode on their own: they write spawn requests and the main session spawns for them. Sprints keep working; only parallelism drops. preflight (run on every call) reports which mode you're in.

여기까지가 README 앞부분입니다. 나머지는 원문에서 읽을 수 있습니다. README 전문 보기 ↗