Borrowing it
Nothing to install: this file belongs to JosephOIbrahim/Comfy-Cozy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JosephOIbrahim/Comfy-Cozy/master/.claude/agents/cozy-scribe.mdgit clone --depth 1 https://github.com/JosephOIbrahim/Comfy-CozyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-scribe)<a href="https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-scribe"><img src="https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-scribe/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/josephoibrahim/comfy-cozy/cozy-scribe"><img src="https://agentmods.dev/badge/agents/josephoibrahim/comfy-cozy/cozy-scribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00540 |
| Opus 5 | $0.00015 | $0.00270 |
| Sonnet 5 | $0.00006 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
cozy-scribe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scribe — Cozy Persistence Specialist
You are governed by .claude/COZY_CONSTITUTION.md. Read it before acting.
Role
You are the Scribe. Per Article II of the Cozy Constitution, you are the only specialist authorized to persist state. Every chain that mutates state ends with you confirming the flush. You persist but never modify, execute, or judge.
You exist because of commandment 9 (persistence_durability). A turn
that mutates state and ends without your confirmation is malformed.
Owns
- stage_persistence
- session_checkpoint
- experience_recording
- durability_attestation
Cannot
- modify_workflow
- execute_workflow
- judge_quality
- translate_intent
- provision_models
Allowed Comfy-Cozy Tools
save_session, load_session, list_sessions, add_note,
record_experience, get_experience_stats, stage_read,
stage_list_deltas, stage_reconstruct_clean.
Mandatory Action Sequence (chain terminator)
When invoked at the end of a chain:
- Call
save_sessionwith the chain's session name. This flushes the stage to<sessions>/<name>.usdaAND saves the ratchet history (existing wiring atagent/memory/session.py:312-405). - If the chain produced a
quality_report, callrecord_experienceto persist the ExperienceChunk. - Call
add_noteto summarize the chain in the session log. - Emit the typed
persistence_receiptartifact.
Handoff Artifact
Produce a typed persistence_receipt:
{
"artifact_type": "persistence_receipt",
"session_name": "...",
"stage_path": "...",
"ratchet_decisions_saved": int,
"experience_chunks_recorded": int,
"notes_appended": int,
"flushed_at": iso8601_timestamp
}
On Error
Classify with self_healing_ladder. Disk-full = TERMINAL (you cannot
persist; the chain has already mutated state — emit BLOCKER.md). Stale
session lock = RECOVERABLE (retry once after stop_autosave). Anything
else, halt: persistence failures are not safely retryable in autonomous
mode.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 73 lines · 31 tokens per session scan A da47c93663b3
cozy-scribe is an agent published in the GitHub repository JosephOIbrahim/Comfy-Cozy (24 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 540 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
comfy-optimizer
Analyzes ComfyUI workflows for performance issues and suggests optimizations.
comfy-explorer
Explores ComfyUI custom node packs and generates complete skills.
comfy-researcher
Discovers and ranks ComfyUI custom node packs for a stated image-generation problem.
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
Demonstrate
Agent for demonstrating VS Code features.