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/gate-p4)<a href="https://agentmods.dev/commands/jonase47/ccpr/gate-p4"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/gate-p4/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/gate-p4"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/gate-p4.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 | $0.02504 |
| Opus 5.5 | $0.00000 | $0.01002 |
| Sonnet 5.5 | $0.00000 | $0.00501 |
| Haiku 4.5 | $0.00000 | $0.00250 |
Grade A, and why
gate-p4 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gate-p4 – Quality Gate 4: Planning → Implementation
Checks whether all organizational and technical prerequisites are met to begin implementation. This is a readiness gate – all participants must know what to do first. No argument – this gate always checks the complete checklist.
No Argument ($ARGUMENTS not applicable)
Gate commands do not accept arguments. They always check the complete current project status.
0. Work-item adoption guard (ADR-0002 §8)
Criterion 6 below ("can the developer start without asking questions?") needs a concrete answer for whether at least one story is actually committed and ready to implement — not just "the backlog looks precise".
Run python3 ~/.claude/scripts/workitems.py list and explicitly check whether the
docs/workitems/ directory exists (e.g. ls docs/workitems/). Both signals are required — list
returns the identical [] for an adopted-but-empty store and a never-adopted project; only the
directory's existence tells them apart, and getting this wrong lets the gate falsely pass a
project with zero committed work.
- Non-empty list → the project uses the structured store. Check
workitems list --status "Ready"for criterion 6: non-empty means/p4-sprinthas committed at least one story (/p5-implementwill find it); empty is a genuine Not Met finding for criterion 6. - Empty list, but
docs/workitems/exists → the store is adopted, just empty for this query. This is a genuine Not Met finding for criterion 6 — the developer has nothing to start on — NOT an exemption to fall back to prose. Do not treat this case the same as "never adopted". - Empty list and no
docs/workitems/directory → not adopted, still on prose. Fall back to reading BACKLOG.md/SPRINT.md prose for criterion 6, as before, and evaluate readiness from the prose story status. Emit one line: "Tip: runliftto adopt the structured work-item store."
See docs/adr/ADR-0002-workitem-backend-contract.md for the adoption-guard rationale and the status
vocabulary.
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.
- 26d ago Changed 073cb9a183df
- 1mo ago Changed 7068a2f5244d
- 1mo ago Changed · +3 lines 7f3f614739bf
- 1mo ago First seen · 171 lines · 0 tokens per session scan A 07b5ebadf40b
gate-p4 is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,504 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 2026-08-31.
Other commands, from other repositories
stats
Show real token usage, delegation rate, and actual savings for the current Hydra session (parses Claude Code session JSONL — no AI estimation).
map
View, rebuild, or query the codebase dependency map.
design-intent
Guided UI/visual development with structured exploration, architecture design, and quality review.
ralph
Ralph autonomous development loop with fresh context per iteration.
debug
Systematic debugging with automated investigation and 4-phase methodology. Default: inline evidence gathering and diagnosis. --deep: spawns systematic-debugger agent for full autonomous debugging. Use for errors, stack traces, test failures, or unexpected behavior.
double-check
Comprehensive verification with automated quality gates, confession gathering, and confidence-based issue filtering. Default: self-review with gates. --deep: multi-agent review via code-reviewer agent. Use before committing, after fixing bugs, or to validate feature completeness.