Cozempic
Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning
Install / Use
/learn @Ruya-AI/CozempicQuality Score
Category
Development & EngineeringSupported Platforms
README
Cozempic
20,000+ power users trust Cozempic to keep their Claude Code sessions lean.
Context cleaning for Claude Code ��� remove the bloat, keep everything that matters, protect Agent Teams from context loss.
What It Does
Claude Code sessions fill up with dead weight: progress ticks, thinking blocks, stale file reads, duplicate CLAUDE.md injections, base64 screenshots, oversized tool outputs, and metadata bloat. A typical session carries 8-46MB — most of it noise that inflates every API call.
Cozempic removes it with 17 composable strategies across 3 prescription tiers, while your actual conversation, decisions, and working context stay untouched. The guard daemon runs automatically — install once, forget about it.
Key Features
- 18 pruning strategies — gentle (5), standard (11), aggressive (18)
- Guard daemon — auto-starts via SessionStart hook, monitors and prunes continuously
- compact-summary-collapse — 85-95% savings by removing pre-compaction messages already in the summary
- Agent Teams protection — checkpoints team state through compaction, reactive overflow recovery
- Behavioral digest — extracts your corrections ("don't do X"), persists them to Claude Code's memory system so they survive compaction
- 8 doctor checks — diagnose and auto-fix session corruption, orphaned tool results, zombie teams
- Token-aware diagnostics — exact token counts from
usagefields, cache hit rate, context % bar - Auto-detects 1M context — correct thresholds for both 200K and 1M models
- Auto-updates — checks PyPI daily, upgrades in-place
Zero external dependencies. Python 3.10+ stdlib only.
Install
pip install cozempic
cozempic init
That's it. The guard daemon auto-starts on every session via hooks. No second terminal needed.
As a Claude Code Plugin
pip install cozempic
Then inside Claude Code:
/plugin marketplace add Ruya-AI/cozempic
/plugin install cozempic
This gives you MCP tools, skills (/cozempic:diagnose, /cozempic:treat, etc.), and auto-wired hooks.
Quick Start
# Auto-detect and diagnose the current session
cozempic current --diagnose
# Dry-run the standard prescription
cozempic treat current
# Apply with backup
cozempic treat current --execute
# Go aggressive on a specific session
cozempic treat <session_id> -rx aggressive --execute
# Check for session corruption
cozempic doctor
# View behavioral digest rules
cozempic digest show
# Show all strategies & prescriptions
cozempic formulary
Strategies
| # | Strategy | Tier | What It Does | Expected |
|---|----------|------|-------------|----------|
| 1 | compact-summary-collapse | gentle | Remove all pre-compaction messages (already in the summary) | 85-95% |
| 2 | attribution-snapshot-strip | gentle | Strip attribution-snapshot metadata entries | 0-2% |
| 3 | progress-collapse | gentle | Collapse consecutive and isolated progress tick messages | 40-48% |
| 4 | file-history-dedup | gentle | Deduplicate file-history-snapshot messages | 3-6% |
| 5 | metadata-strip | gentle | Strip token usage stats, stop_reason, costs | 1-3% |
| 6 | thinking-blocks | standard | Remove/truncate thinking content + signatures | 2-5% |
| 7 | tool-output-trim | standard | Trim large tool results (>8KB or >100 lines), microcompact-aware | 1-8% |
| 8 | tool-result-age | standard | Compact old tool results by age — minify mid-age, stub old | 10-40% |
| 9 | stale-reads | standard | Remove file reads superseded by later edits | 0.5-2% |
| 10 | system-reminder-dedup | standard | Deduplicate repeated system-reminder tags | 0.1-3% |
| 11 | tool-use-result-strip | standard | Strip toolUseResult envelope field (Edit diffs, never sent to API) | 5-50% |
| 12 | image-strip | aggressive | Strip old base64 image blocks, keep most recent 20% | 1-40% |
| 13 | http-spam | aggressive | Collapse consecutive HTTP request runs | 0-2% |
| 14 | error-retry-collapse | aggressive | Collapse repeated error-retry sequences | 0-5% |
| 15 | background-poll-collapse | aggressive | Collapse repeated polling messages | 0-1% |
| 16 | document-dedup | aggressive | Deduplicate large document blocks (CLAUDE.md injection) | 0-44% |
| 17 | mega-block-trim | aggressive | Trim any content block over 32KB | safety net |
| 18 | envelope-strip | aggressive | Strip constant envelope fields (cwd, version, slug) | 2-4% |
Prescriptions
| Prescription | Strategies | Risk | Typical Savings |
|---|---|---|---|
| gentle | 5 | Minimal | 85-95% (with compact boundary) |
| standard | 11 | Low | 25-45% |
| aggressive | 18 | Moderate | 35-60% |
Dry-run is the default. Nothing is modified until you pass --execute. Backups are always created.
Guard — Continuous Protection
The guard daemon monitors your session and prunes automatically:
# Auto-starts via SessionStart hook after cozempic init
# Or run manually:
cozempic guard --daemon
4-tier proactive pruning (every 30s):
| Tier | Threshold | Action | Reload? | |------|-----------|--------|---------| | Soft | 25% | gentle file cleanup | No | | Hard | 55% | standard prune | Yes (deferred if agents active) | | Emergency | 80% | aggressive prune | Yes (forced) | | User | 90% | manual aggressive | Yes |
Reactive overflow recovery — kqueue/polling file watcher detects inbox-flood overflow within milliseconds, auto-prunes with escalating prescriptions, circuit breaker prevents loops.
tmux/screen — reload resumes in the same pane via send-keys. Plain terminals open a new window.
Token thresholds auto-detect — 200K and 1M models detected automatically. Override with COZEMPIC_CONTEXT_WINDOW=200000 for Pro plan.
Behavioral Digest
Cozempic extracts your corrections and persists them across compactions:
# View extracted rules
cozempic digest show
# Manually extract from current session
cozempic digest update
# Sync rules to Claude Code's memory system
cozempic digest inject
How it works:
- Detects correction signals in your messages ("don't do X", "stop adding Y", "always use Z")
- Explicit corrections activate immediately; implicit corrections need 2 occurrences
- Rules synced to Claude Code's native memory system (
~/.claude/projects/<cwd>/memory/) - Claude reads these as feedback memories on every turn — they survive compaction natively
- PreCompact and Stop hooks auto-extract before context is lost
Agent Teams Protection
When Claude's auto-compaction fires, Agent Teams lose coordination state. Cozempic prevents this with five layers:
- Continuous checkpoint — saves team state every N seconds
- Hook-driven checkpoint — fires after every Task spawn, TaskCreate/Update, before compaction, at session end
- Tiered pruning — soft threshold trims without disruption; hard threshold does full prune + reload
- Reactive overflow recovery — detects inbox-flood within milliseconds, auto-recovers (~10s downtime)
- is_protected() — compact summaries, compact boundaries, content-replacement entries, and behavioral digest messages are never stripped
Doctor
cozempic doctor # Diagnose issues
cozempic doctor --fix # Auto-fix where possible
| Check | What It Detects | Auto-Fix |
|-------|----------------|----------|
| trust-dialog-hang | Resume hangs on Windows | Reset flag |
| claude-json-corruption | Truncated/corrupted JSON | Restore from backup |
| corrupted-tool-use | tool_use.name >200 chars | Parse and repair |
| orphaned-tool-results | tool_result missing matching tool_use — causes 400 errors | Strip orphans |
| zombie-teams | Stale team directories with dead agents | Remove stale dirs |
| oversized-sessions | Session files >50MB | — |
| stale-backups | Old .jsonl.bak files wasting disk | Delete old backups |
| disk-usage | Session storage exceeding healthy thresholds | — |
Commands
cozempic init Wire hooks + slash command into project
cozempic list List sessions with sizes and token estimates
cozempic current [-d] Show/diagnose current session
cozempic diagnose <session> Analyze bloat sources
cozempic treat <session> [-rx PRESET] Run prescription (dry-run default)
cozempic treat <session> --execute Apply changes with backup
cozempic strategy <name> <session> Run single strategy
cozempic reload [-rx PRESET] Treat + auto-resume in new terminal
cozempic checkpoint [--show] Save team state to disk
cozempic guard [--daemon] Start guard (auto-starts via hook)
cozempic doctor [--fix] Check for known issues
cozempic digest [show|update|clear|flush|recover|inject]
cozempic self-update Upgrade to latest version from PyPI
cozempic formulary Show all strategies & prescriptions
Hook Integration
After cozempic init, these hooks are wired automatically:
| Hook | When | What |
|------|------|------|
| SessionStart | Session opens | Guard daemon + digest inject |
| PostToolUse[Task] | Agent spawn | Team checkpoint |
| PostToolUse[TaskCreate\|TaskUpdate] | Todo changes | Team checkpoint |
| PreCompact | Before compaction | Checkpoint + digest flush |
| Stop | Session end | Checkpoint + digest flush |
Safety
- Dry-run by default —
--executerequired to modify files - Atomic writes —
write → fsync → os.replace()— no partial writes - Strict session resolution — refuses to act on ambiguous matches
- Timestamped backups — automatic
.jsonl.bakbefore any modification - is_protected()
Related Skills
node-connect
351.4kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
claude-opus-4-5-migration
110.7kMigrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5
frontend-design
110.7kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
model-usage
351.4kUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
