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/utility)<a href="https://agentmods.dev/commands/jonase47/ccpr/utility"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/utility/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/utility"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/utility.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 | $0.01015 |
| Opus 5.5 | $0.00000 | $0.00406 |
| Sonnet 5.5 | $0.00000 | $0.00203 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
utility 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 1mo 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Utility (14 commands)
Cross-cutting commands that operate outside the phase flow.
| Command | Title | Description |
|---|---|---|
/anchor |
Anchored State Verification (Docs vs. Implementation) | Checks phase documents against the code they describe, not against other documents. Stage 1 is a mechanical delta (anchor status/check) between a document's anchor_commit and the last production-code commit — always exit 0, staleness is data, never a verdict. Stage 2 asks, scoped to the delta only, whether it invalidates a statement in the document; only "yes" opens a work item. anchor ack acknowledges drift deliberately (never a side effect of another command); anchor set (normally via the freeze hook on Gate-Go) writes the anchor onto the phase index. Design: docs/adr/ADR-0009-anchored-state-verification.md. |
/cleanup |
Doc Hygiene: HANDOVER cap + lint aggregator | 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 three existing lint scripts (memory-lint.sh, phase-docs-lint.sh, doc-volume-check.sh) bundled into one consolidated drift report. Use this between phases (after a Gate) or whenever the project-guide warns about HANDOVER size, an unprocessed inbox, stale memory or doc volume drift. |
/decision |
Develop a decision basis | 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. |
/epic |
Create an epic | 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. |
/guide |
Project Guide (Status, Command Recommendation, Disambiguation) | 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. |
/konzept-update |
Revise an existing rough concept | This command updates an existing rough concept based on new findings, clarified open questions, or changed requirements. Each revision is versioned and timestamped so that the evolution of the concept remains traceable. |
/konzept |
Create a rough concept for a feature or (sub-)project | This command guides through the initial conception phase as a Product Owner. The result is a first structured rough concept that serves as the basis for further steps (user stories, roadmap, stakeholder presentation). |
/logs-summary |
Log summary | Analyzes and summarizes the agent monitor logs. |
/project-init |
Project initialization | Initializes a new project with directory structure, project-specific CLAUDE.md, and Git repository. |
/release-baseline |
Set project state as baseline | Makes a "cut" after a release: project state is documented as given, HANDOVER is archived and summarized, docs are split into Frozen/Active. |
/roadmap-update |
Update an existing roadmap | This command updates an existing roadmap based on new findings, completed milestones, changed priorities, or new decisions. Each revision is versioned and timestamped with date + time. |
/roadmap |
Create an initial roadmap | This command creates a first roadmap based on an existing rough concept. The roadmap structures epics, milestones, and dependencies either time-based (quarters/months) or phase-based (MVP, Phase 1, Phase 2...) – selectable depending on the project character. |
/specialize |
Adapt agents to the project's tech stack | Writes project-local specialized copies of the technical agents (senior-developer, code-reviewer, qa-tester, debugger, devops, …) under .claude/agents/ and injects a marker-delimited Project Tech Context block with stack-specific correctness/security/idiom rules per persona. docs mode reads the P3 TECH_STACK.md + ADRs; codebase mode scans an existing codebase's manifests + CI config. No auto-commit, no blind overwrite, ⚠ verify instead of invented facts. |
/user-stories |
Create or elaborate user stories | This command creates detailed user stories – either derived from an existing epic, roadmap, or concept, or standalone from a free description. Each story contains acceptance criteria, priority, dependencies, and a definition of done. |
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.
- 1mo ago Changed bc84320e9297
- 1mo ago First seen · 28 lines · 0 tokens per session scan A 27c6c686a631
utility is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,015 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.