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.
git 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-sprint)<a href="https://agentmods.dev/commands/jonase47/ccpr/p4-sprint"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p4-sprint/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/commands/jonase47/ccpr/p4-sprint"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p4-sprint.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 | $0.00000 | $0.04309 |
| Opus 5.5 | $0.00000 | $0.01724 |
| Sonnet 5.5 | $0.00000 | $0.00862 |
| Haiku 4.5 | $0.00000 | $0.00431 |
Grade A, and why
p4-sprint 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 29d 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p4-sprint – Plan Sprint
Plans the current sprint: pulls matching stories from the backlog, defines the sprint goal, identifies risks, and creates the sprint document. Called repeatedly at the start of each new sprint.
Argument: $ARGUMENTS = [Sprint goal, e.g. "Complete auth flow", "MVP core running"]
If provided: Use as the sprint goal and select matching stories that support this goal, resolved via
the work-item adoption guard below (falls back to reading BACKLOG.md prose, if the project is still
on prose).
If not provided: Read PROJECT_PLAN.md and derive a sensible sprint goal from the available story
candidates (guard below). If no candidate stories exist, point this out and recommend running
/p4-backlog first.
0. Work-item adoption guard (ADR-0002 §8)
/p4-backlog creates every story at Backlog (unstarted, re-selectable). Ready means
"committed to a sprint" — nothing sets it except this command, when it actually pulls a story into
the Sprint Table (step 2B). So the candidate POOL is Backlog, not Ready; /p5-implement
correctly resolves its own selection from Ready, because this command is what populates it.
Run python3 ~/.claude/scripts/workitems.py list.
- Non-empty array → the project uses the structured store. Select candidate stories via
workitems list --status "Backlog"(step 2B) instead of reading BACKLOG.md prose for candidates — BACKLOG.md/backlog/E-0X-*.mdremain readable for the full story text (title, description, acceptance criteria) once a candidate's id is known, but the candidate SET itself comes from the CLI, not from re-parsing prose. []and nodocs/workitems/directory → still on prose. Read BACKLOG.md for candidate stories, as before. Emit one line: "Tip: runliftto adopt the structured work-item store."[]butdocs/workitems/exists → adopted store, just empty right now (e.g. everything already committed to a sprint or done). Treat as adopted: use the CLI — an emptyBackloglist means no candidate stories, not "fall back to prose".
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.
- 29d ago Changed · +6 lines 0344e6c919fb
- 1mo ago Changed 222c576d8492
- 1mo ago Changed c62bea4036f1
- 1mo ago First seen · 290 lines · 0 tokens per session scan A b5e7e204bec2
p4-sprint is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,309 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
loops
Weekly review — surface everything in-flight and force a ship / block / kill decision on each.
ralph
Ralph autonomous development loop with fresh context per iteration.
create-prd
Create PRD and set up project for Ralph autonomous development loop.
config
Configure team-management (non-secret settings) through a guided menu.
forge-status
Show registry of all managed projects with scores, trends, and alerts.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.