CCPR is a phase-based project framework for Claude Code
This repository also configures its own agents. See what ccpr tells them →
Command Claude Code
Quality gates between phases — single-purpose decision points. Main gates (P0–P7) plus sub-gates for the dual-approval gates P6 (QA + Security) and P7 (Tech + Business).
Command Claude Code
Meta-commands for capturing session insight back into the system.
Command Claude Code
All P0–P8 phase commands grouped per phase. Lead commands appear first, then sub-commands in execution sequence where applicable.
Command Claude Code
Entry-point and cross-cutting commands. /track-decision runs first; the others compose Lean-Track / Full-Track / consistency checks.
Command Claude Code
Cross-cutting commands that operate outside the phase flow.
Command Claude Code
Checks phase documents against the code they describe, not against other documents. Where /cross-check compares Markdown to Markdown, /anchor compares a document's declared anchorcommit to the repository's actual history — the two-stage check design of docs/adr/ADR-0009-anchored-state-verification.md (both addenda).
Command Claude Code
Runs a one-shot hygiene pass on a project's docs to keep them lean and machine-readable: HANDOVER inbox triage and size cap enforcement plus the four existing lint scripts (memory-lint.sh, phase-docs-lint.sh, doc-volume-check.sh, manual-lint.sh) bundled into one consolidated drift report. Use this between phases…
Command Claude Code
Creates or updates docs/CONSTITUTION.md — the project Constitution with three sections (Inviolable / Default / Aspirational). Read as a mandatory input by all Full-Track Gates and used as a consistency check for every ADR and implementation decision.
Command Claude Code
Reads phase indexes and selected detail files, checks inconsistencies between phases (architecture ↔ implementation, features ↔ stories, threats ↔ mitigations, etc.).
Command Claude Code
This command analyzes an open decision question, automatically determines which perspectives are relevant, assembles the appropriate analysis agents, and develops a structured decision basis (Decision Basis) – without making the decision itself. That is the PO's responsibility.
Command Claude Code
This command creates one or more epics – either derived from an existing concept or roadmap, or standalone from a free description. An epic can already contain rough associated user stories or be created as a pure high-level shell – this is selectable per call.
Command Claude Code
Checks whether all criteria of the Discovery phase have been met and prepares the Go/No-Go Decision. No argument – this gate always checks the complete checklist.
Command Claude Code
Checks whether all results of the conception phase are complete and robust, and prepares the transition to the validation phase. No argument – this gate always checks the complete checklist.
Command Claude Code
Checks whether all critical Assumptions have been validated and a well-founded Go/No-Go/Pivot Decision can be made. This is the most important gate in the model – here it is decided whether to invest in the cost- and time-intensive architecture and implementation phase. No argument – this gate always checks the…
Command Claude Code
Checks whether all architecture and design decisions are completely documented and robust before transitioning into the planning and implementation phase. No argument – this gate always checks the complete checklist.
Command Claude Code
Checks whether all organizational and technical prerequisites are met to begin implementation. This is a readiness gate – all participants must know what to do first. No argument – this gate always checks the complete checklist.
Command Claude Code
Checks at the end of each sprint whether all tasks meet quality standards and the sprint can be considered successfully completed. Called repeatedly after each sprint. No argument – this gate always checks the complete current sprint status.
Command Claude Code
Evaluates all QA-relevant points of the Gate-P6 checklist and grants QA approval.
Command Claude Code
Evaluates all security-relevant points of the Gate-P6 checklist and grants Security approval.
Command Claude Code
Checks whether the system is ready for launch. Both QA and Security must explicitly grant approval. No go-live without dual approval.
Command Claude Code
Checks business readiness: documentation, GTM, KPIs, legal mandatory documents.
Command Claude Code
Checks technical go-live readiness: deployment, monitoring, rollback, smoke tests.
Command Claude Code
Checks whether the system is fully ready for production operation. Last gate before the official go-live status.
Command Claude Code
Invokes the project-guide agent as the entry point for the current project: structured status snapshot, prioritised next steps with command/agent recommendation, and disambiguation for unclear requests.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: