finalize
Perform snapshot QA and one in-place repair pass. Dispatch only when Step 5 `lint`, `check`, or snapshot review reports a defect. The orchestrator owns final approval and render; this agent never renders.
$ npx -y skills add coco-research/coco --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Perform snapshot QA and one in-place repair pass. Dispatch only when Step 5 `lint`, `check`, or snapshot review reports a defect. The orchestrator owns final approval and render; this agent never renders.
Agent definition
finalize.mdFinalize / repair subagent
Perform snapshot QA and one in-place repair pass. Dispatch only when Step 5 `lint`, `check`, or snapshot review reports a defect. The orchestrator owns final approval and render; this agent never renders.
Dispatch context
`SKILL_DIR` / `PROJECT_DIR` / proof snapshot times / `lint` and `check` output tails, when present.
Flow
1. **Snapshots** — run `npx hyperframes snapshot --at <proof-times>` and inspect overflow, off-canvas content, text collisions, empty frames, wrong content, and unreadable motion. 2. **One in-place repair pass** — edit `compositions/index.html` for the visible issues. Never change a fixed `data-duration`; timing is set upstream. 3. **Recheck** — rerun `npx hyperframes lint`, `npx hyperframes check`, and the affected snapshots. Return the result to the orchestrator without rendering.
STOP / escalate
Only when the shot is **fundamentally wrong** (whole content off, needs recomposition) — return to Step 3/4 (re-design + re-build), don't force it with edits. Small fixes never escalate.
Meet Coco. A superintelligent agent framework powered by an advisory board of 389 world-class minds. Scale your AI assistant into a complete engineering department with 142 skills, 277 commands, and persistent state. Universal compatibility. Local privacy. Free and open source.
Repo: coco-research/coco
Other agents on coco.
- ai-engineer
Senior AI engineer for architecting, implementing, and optimizing end-to-end AI systems — from model selection and training pipelines to production deployment, monitoring, and ethical governance. Use proactively when designing AI architectures, selecting models, building
Open agent - code-reviewer
Senior code and architecture reviewer for comprehensive quality, security, performance, and architectural integrity analysis. Use proactively after writing or modifying code, before merging PRs, when reviewing structural changes, designing services, or evaluating API
Open agent - data-specialist
Senior data specialist covering exploratory analysis, statistical modeling, machine learning, experimentation, SQL optimization, query design, and performance tuning across major database platforms. Use proactively when analyzing datasets, building predictive models, running A/B
Open agent - database-architect
Database architecture and design specialist. Use PROACTIVELY for database design decisions, data modeling, scalability planning, microservices data patterns, database technology selection, migration strategies, and performance optimization.
Open agent - mcp-specialist
MCP (Model Context Protocol) specialist covering server/client development, configuration, troubleshooting, tool setup, architecture, transport layers, and protocol compliance against the MCP 2025-06-18 spec. Use proactively when building MCP servers, configuring MCP
Open agent - pm-advisor
Product management advisor for feature planning, issue creation, prioritization, and data-driven product decisions. Use proactively when planning features, writing user stories, creating GitHub/Jira issues, prioritizing a backlog, defining acceptance criteria, structuring epics,
Open agent