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/rtazima/claude-proj-blueprintWrote 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/rtazima/claude-proj-blueprint/ralph)<a href="https://agentmods.dev/commands/rtazima/claude-proj-blueprint/ralph"><img src="https://agentmods.dev/badge/commands/rtazima/claude-proj-blueprint/ralph/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/rtazima/claude-proj-blueprint/ralph"><img src="https://agentmods.dev/badge/commands/rtazima/claude-proj-blueprint/ralph.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 | $0.00185 |
| Opus 5.5 | $0.00000 | $0.00074 |
| Sonnet 5.5 | $0.00000 | $0.00037 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
ralph 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.
What it actually says
Persistence mode: implement from PRD and don't stop until all acceptance criteria pass.
Arguments: $ARGUMENTS (PRD path, e.g. docs/product/feat-auth.md)
Workflow:
- Activate the
persistenceskill - Read the PRD at $ARGUMENTS
- Extract all acceptance criteria into a checklist
- Read CLAUDE.md for test/build commands
- Enter the persistence loop:
- Implement changes to address failing criteria
- Run tests/build after each change
- Report which criteria pass/fail
- Continue until ALL pass or max iterations (default: 5) reached
- After loop completes, run slop-cleaner on changed files
- Run documentation checklist from /implement (step 8)
- Commit with Conventional Commits format
Do NOT ask for confirmation between iterations. The boulder never stops.
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 First seen · 20 lines · 0 tokens per session scan A 46af87ece4a3
ralph is a command published in the GitHub repository rtazima/claude-proj-blueprint (22 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 185 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 2026-08-30.
Other commands, from other repositories
onboarding-pack
Developer onboarding package for first hire or agency handoff.
technical-roadmap
Phased delivery plan with milestones, dependencies, risk gates, and resource planning.
sync-backlog
Push sprint backlog from a blueprint into Azure DevOps or Jira as sprints and work items.
sprint-status
Show current sprint progress by cross-referencing backlog with activity logs.
reconcile
Explain unmapped code changes and fold them into the VibeFrame model.
pm
Product manager analysis — milestone triage, issue prioritization, release planning.