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/epic)<a href="https://agentmods.dev/commands/jonase47/ccpr/epic"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/epic/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/epic"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/epic.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 | $0.01380 |
| Opus 5.5 | $0.00000 | $0.00552 |
| Sonnet 5.5 | $0.00000 | $0.00276 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
epic 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/epic – Create an epic
Purpose
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.
Execution
Step 1 – Load context
Check whether the user named a source file:
- Concept file → read from
docs/concepts/ - Roadmap → read from
docs/roadmaps/ - Both → read both and merge
- No file → standalone, work only with the description from the prompt
If no source file and no sufficient description is available:
"Describe the epic briefly or give me a concept/roadmap file as a basis."
Step 2 – Clarify scope
Ask once if not specified in the prompt:
"Should the epic already contain rough user stories, or just create the high-level shell? (a) Shell + rough user stories (b) Epic shell only"
Also, if derived from concept/roadmap and multiple epics are recognizable:
"I see [X] possible epics. All at once or select a specific one?"
Step 3 – Parallel analysis by sub-agents
Start three sub-agents in parallel using the Task tool.
Mark ambiguities as [UNCLEAR: ...].
Sub-Agent A – Epic definition & goal
- What is the overarching goal of this epic from the user's perspective?
- What value does the epic deliver when it is complete?
- How does it differ from other epics?
- Which user groups are affected?
Sub-Agent B – Scope & content
- What belongs in this epic (in scope)?
- What deliberately does not belong (out of scope)?
- If variant (a) selected: which user stories can be roughly derived? Format per story: "As a [role] I want [action] so that [benefit]."
- Rough effort estimate: Small / Medium / Large
Sub-Agent C – Dependencies & risks
- Does this epic depend on other epics or decisions?
- What must be complete before this epic?
- What risks or blockers exist?
- Are there technical or functional prerequisites?
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 1d133604921b
- 1mo ago Changed · +3 lines eaef44235bea
- 1mo ago First seen · 181 lines · 0 tokens per session scan A 407a67dbacbf
epic 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 1,380 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.