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.
npx agentmods add commands/jonase47/ccpr/guidegit clone --depth 1 https://github.com/jonase47/ccprWhat 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 | $0.00000 | $0.01078 |
| Opus 5 | $0.00000 | $0.00539 |
| Sonnet 5 | $0.00000 | $0.00216 |
| Haiku 4.5 | $0.00000 | $0.00108 |
Grade A, and why
guide 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 yesterday.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/guide – Project Guide (Status, Skill Recommendation, Disambiguation)
Invokes the project-guide agent as the entry point for the current project:
structured status snapshot, prioritised next steps with skill/agent
recommendation, and disambiguation for unclear requests.
Argument: $ARGUMENTS = [optional: concrete question / request]
- Without argument: status snapshot + 3 prioritised next steps.
- With argument: disambiguate the request and hand off to the matching domain agent, with 1–2 clarifying questions first if needed.
Execution
- Work-item adoption guard (ADR-0002 §8) —
project-guidehas no Bash access (by design, it's read-only via Read/Grep/Glob/Edit), so if the active phase is P4/P5, the orchestrator resolves this beforehand and passes the result in. Runpython3 ~/.claude/scripts/workitems.py listand explicitly check whether thedocs/workitems/directory exists (e.g.ls docs/workitems/) — both signals are required,listreturns the identical[]for an adopted-but-empty store and a never-adopted project.- Non-empty list → the project uses the structured store. A bare
list --status "Ready"/"In Progress"/"Done"returns PROJECT-WIDE totals across every sprint, not this sprint's. Scope it: read the current sprint number<N>fromdocs/planning/SPRINT.md's frontmattersprint: <N>(or the activedocs/planning/sprint/SPRINT-NN.md'ssprint: NNfield, for the sub-index layout), then runworkitems list --sprint <N>and count status directly among that result. Report the scoped counts as "this sprint" (e.g. "6/10 Done, 2 In Progress, 2 Ready — this sprint"). If SPRINT.md (or the active sprint detail file) carries nosprint:frontmatter yet (a sprint plan predating this convention, or before the project's first/p4-sprintrun under it), scoping isn't possible — report the unscopedlist/--statuscounts but label them explicitly "project-wide", never "this sprint". - Empty list, but
docs/workitems/exists → the store is adopted, just empty right now (or genuinely zero items). Report it as such (e.g. "0 items adopted yet" or "0 in this sprint"), don't fall back to prose. - Empty list and no
docs/workitems/directory → not adopted, still on prose. Derive sprint status from SPRINT.md as before.
- Non-empty list → the project uses the structured store. A bare
- Start the
project-guideagent via the Task tool, passing the resolved item counts (if any, labeled "this sprint" or "project-wide" per the scoping above) as part of its context. - Pass the argument (if present) as the request.
- The guide operates read-only on:
.claude/CLAUDE.mddocs/HANDOVER.mddocs/.session-context.md(if <10 min old)docs/memory/MEMORY.mddocs/BASELINE.md(if Baseline mode is active)- Phase-specific files (SPRINT.md, phase indexes) if needed
~/.claude/docs/NEXT_STEPS_REFERENCE.mdas the phase-sequence reference- Work-item counts prepared by the orchestrator in step 1 (structured-store projects)
- Write permissions for the guide are limited to
docs/memory/project-guide/and its HANDOVER section.
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.
- yesterday First seen · 85 lines · 0 tokens per session scan A 80c72d8615ed
guide is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,078 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
drift
Post-implementation spec drift check — verify the implementation matches existing OpenSpec specifications.
feature
Orchestrate a complete feature through discovery, spec, implementation, and review.
research
Research a technical or product question.
tidy
Consistency check for non-code repos with INDEX.md hierarchy. Verifies INDEX.md accuracy, MEMORY.md references, orphaned files, stale dates, and WAITING markers.
clean-check
Analyze code for cleanliness issues (unused code, comment quality, formatting, naming, complexity). Delegates to the code-cleanliness agent.
build
Mini spec-first development workflow for well-scoped implementation tasks with human in the loop.