Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/jonase47/ccpr/p4-backloggit clone --depth 1 https://github.com/jonase47/ccprWrote 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/commands/jonase47/ccpr/p4-backlog)<a href="https://agentmods.dev/commands/jonase47/ccpr/p4-backlog"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p4-backlog.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.03124 |
| Opus 5 | $0.00000 | $0.01562 |
| Sonnet 5 | $0.00000 | $0.00625 |
| Haiku 4.5 | $0.00000 | $0.00312 |
Grade A, and why
p4-backlog 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 yesterday.
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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p4-backlog – Work Breakdown, Backlog & Milestones
Breaks down the features from FEATURES.md into actionable tasks, builds the prioritized backlog, and defines milestones and release planning. The result is BACKLOG.md and PROJECT_PLAN.md as the steering foundation for the entire implementation.
Argument: $ARGUMENTS = [Focus Epic, e.g. "Authentication", "Booking Process", "Admin Area"]
If provided: Work out the named epic in particular detail – other epics may remain at a higher level. If not provided: Read FEATURES.md, MVP.md and ARCHITECTURE.md and create a complete backlog for all must-have features. If any context is missing, ask about the MVP scope.
Execution
1. Read Context
Read the following files (if available):
- FEATURES.md / MVP.md (feature scope and prioritization)
- ARCHITECTURE.md / DATA_MODEL.md / API_SPEC.md (technical foundation)
- SECURITY.md (security requirements as mandatory tasks)
- DSGVO_INITIAL_ASSESSMENT.md (DSGVO (GDPR) mandatory tasks)
- FINANCIAL_PLAN.md (budget constraints influence scheduling)
2. Delegation to Project-Planner Agent (Lead)
Delegate the backlog build to the project-planner agent:
Build the project backlog. Focus epic (if provided): $ARGUMENTS Context: [Insert FEATURES.md, MVP.md, ARCHITECTURE.md key points]
A. Epic Structure Group all must-have features into meaningful epics (4–8 epics for an MVP). Per epic: name, short description, included features, estimated effort (rough story points or days).
B. User Stories & Tasks Break each epic down into user stories:
- Format: "As a [Persona] I want to [Action] so that [Benefit]."
- Acceptance criteria (2–4 points that make it clear when the story is done)
- Technical tasks per story (concrete implementation steps)
- Effort estimate (story points: 1 / 2 / 3 / 5 / 8)
- Dependencies on other stories
- Labels: Frontend / Backend / Fullstack / DevOps / Design
C. Backlog Prioritization
- Sort stories by priority within each epic
- Identify the critical path: which stories block others?
- Mark technical foundation stories (must be implemented first)
D. Milestones & Release Planning
- Define 2–4 milestones on the way to the MVP launch
- Per milestone: name, included epics/stories, criterion for completion
- Initial time estimate: how many sprints (2 weeks each) are needed?
E. Risks & Buffers
- Which stories have the highest uncertainty?
- Where should buffers be planned?
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.
- yesterday First seen · 230 lines · 0 tokens per session scan A b5996ac20703
p4-backlog is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,124 tokens. 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 2026-09-03.
Other commands, from other repositories
commands
本文件只记录“本项目管理/协作/治理相关”的元指令，定位类似项目协作协议。不要收录 package 命令、产品 CLI 命令、部署脚本命令或业务执行命令；这些内容应写入对应产品、功能或发布文档。.
factory-ticket
Implement exactly one already-claimed Linear ticket in the current worktree.
factory-report
Linear status report across configured repos — queue depth, triage backlog, ready-to-dispatch, blocked/held.
factory-sweep
Find Linear tickets that have gone obsolete (duplicate, already shipped, overtaken by events) and retire them with evidence.
get-to-work
Autonomous ops work. Args: [mode] [repeat]. Modes: tasks | opps | full | escalating (default). Repeat: cycle (keep going, default) | once (single pass). Run this before stepping away from an ops repo.
factory-audit
Audit this repo against the project-conventions baseline; file the gaps to Linear.