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/decision)<a href="https://agentmods.dev/commands/jonase47/ccpr/decision"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/decision/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/decision"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/decision.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 | $0.01486 |
| Opus 5.5 | $0.00000 | $0.00594 |
| Sonnet 5.5 | $0.00000 | $0.00297 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade A, and why
decision 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/decision – Develop a decision basis
Purpose
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.
Execution
Step 1 – Understand the decision question
Check whether the user has clearly described the decision question.
If not clear, ask once:
"What exactly needs to be decided, and are there already known options – or do those need to be developed first?"
If an existing concept file was referenced (e.g. from /konzept
or /konzept-update): read it and extract the relevant open question.
Step 2 – Determine decision type & select agents
Analyze the decision question and independently determine which perspectives are necessary for a well-founded decision.
Select from the following agent types – only those actually relevant for this decision:
| Agent | When to use |
|---|---|
| Technology Agent | For tech stack, tool, or architecture decisions |
| Effort Agent | When implementation effort or complexity needs to be estimated |
| Risk Agent | For decisions with potential dependencies, vendor lock-in, or operational risks |
| User Agent | When the decision affects usability or user experience |
| Strategy Agent | For decisions with long-term impact on extensibility or direction |
| Cost Agent | When licensing, hosting, or operating costs are relevant |
| Alternatives Agent | When options still need to be developed or are incomplete |
Briefly communicate to the user which agents you are using and why:
"For this decision I'm consulting the following perspectives: [Agent A] – because ..., [Agent B] – because ..., [Agent C] – because ..."
Step 3 – Parallel analysis by the selected agents
Start all selected agents in parallel using the Task tool.
Each agent receives the decision question, the known options (if available)
and the relevant context (e.g. concept file content).
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 162f00965986
- 1mo ago Changed · +3 lines 273ede75715d
- 1mo ago First seen · 182 lines · 0 tokens per session scan A 1a4036f7e409
decision 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 1,486 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.