FCoP Protocol commentary (behavior governance protocol layer · v3 — lifecycle/-based collaboration) — the protocol commentary on the rules defined in fcop-rules.mdc. Covers file naming, YAML frontmatter, v3 lifecycle/ directory layout, lifecycle state machine, patrol triggers, and other practical conventions.…
FCoP Rules (behavior governance protocol layer · v3 — agent runtime contract for lifecycle/-based collaboration) — the protocol rules every agent must follow inside an FCoP project. Auto-deployed by the fcop MCP. Companion file fcop-protocol.mdc explains how each rule applies in practice. FCoP 协议规则(行为治理协议层 · v3 —…
A set of rules for an AI developer role in a file-based team workflow. It explains which task files the developer may process, how to mark work in progress, and how to report the result.
A set of Cursor rules for an AI project manager role, written in Chinese. It defines which task files the role accepts, how it assigns work to other roles, how it tracks results, and how it reports completion.
DEPRECATED path only. FCoP 0.6+ normative rules are fcop-rules.mdc + fcop-protocol.mdc under src/fcop/rules/data/. This file is kept so old URLs do not 404; do not copy it as the live protocol. 仅保留路径防 404,勿再当作权威规范复制到 .cursor/rules/。.
stdio MCP server for the FCoP Python library: exposes the fcop package's Project, task, report, issue, GAL alert, and audit APIs to MCP clients (Cursor, Claude Desktop, …). Optional bridge, not a second protocol; depends on fcop 3.x, FastMCP, websockets. Runs locally from the fcop-mcp Python package. Needs 1…
Review CodeFlowMu proposals for boundary violations. Use when an architect needs to check MCP vs Playbook separation, lifecycle authority, REPORT/EVAL/TASK semantics, public-submission safety, PM runtime ID preservation, or protocol-change risk.
Prepare or review architecture decision notes without adopting ADRs automatically. Use when an architect needs to compare options, recommend a decision, name authority, or ensure a decision note does not become an FCoP protocol change without governance.
Produce CodeFlowMu/FCoP-aware system designs before implementation. Use when an architect needs to define problem, current architecture, proposed design, interfaces, alternatives, risks, and verification without creating runtime behavior by default.
Use when an agent needs to operate or verify a web page with Playwright, including screenshots, viewport checks, navigation, forms, clicks, canvas visibility, responsive layout, or local Panel/browser behavior.
Control approved enterprise Web applications as a digital employee through CodeFlowMu-managed Google Chrome or Microsoft Edge. Use when a Cursor Agent must open an approved Web target, inspect visible DOM controls, click, fill forms, select options, securely fill saved credentials, upload user-authorized local files…
Use when an agent needs to locate relevant files, symbols, call sites, routes, tests, configs, or ownership boundaries before editing or explaining code.
An evaluation tool that observes task flows and records specific patterns, such as probes, self-created tasks, sandbox setup, and project-tree structures. It writes structured findings to observation reports and an emergence log.
Locate relevant CodeFlowMu code and documentation before editing. Use when DEV needs to search with rg, identify candidate files, understand ownership boundaries, or decide whether a task is ready for patching.
Make narrowly scoped CodeFlowMu changes using existing patterns. Use when DEV needs to patch code, docs, manifests, or tests without broad refactors or runtime boundary violations.
Verify and explain DEV changes for PM, QA, or ADMIN review. Use when DEV needs to run tests, summarize evidence, list residual risk, and prepare a truthful FCoP REPORT.
Write CodeFlowMu EVAL observations with evidence, impact, confidence, and follow-up. Use when EVAL notices behavior, UX, governance, implementation, or documentation gaps without turning them into REPORTs.
Advise how EVAL findings should be promoted. Use when EVAL needs to suggest local task, CodeFlowMu issue draft, FCoP issue draft, or hold while applying public safety boundaries and ADMIN approval requirements.
Analyze CodeFlowMu risks and gaps from EVAL findings. Use when EVAL needs to classify expected vs actual behavior, risk type, severity recommendation, evidence, and owner.
Summarize CodeFlowMu logs into actionable evidence. Use when OPS needs to inspect runtime, analytics, usage, or panel logs and distinguish evidence from inference.
Check CodeFlowMu runtime, Panel, project root, and FCoP directory health. Use when OPS needs environment checks, health status, project-root diagnosis, or safe escalation without deleting state.
Diagnose stuck CodeFlowMu tasks, reports, lifecycle states, or agent sessions. Use when OPS needs to identify current state, expected next state, blocker type, and safe recovery owner.