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 skills add rp1-run/rp1 --skill blueprintgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/skills/rp1-run/rp1/blueprint)<a href="https://agentmods.dev/skills/rp1-run/rp1/blueprint"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/blueprint/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/skills/rp1-run/rp1/blueprint"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/blueprint.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 | $0.00019 | $0.02954 |
| Opus 5 | $0.00010 | $0.01477 |
| Sonnet 5 | $0.00004 | $0.00591 |
| Haiku 4.5 | $0.00002 | $0.00295 |
Grade A, and why
blueprint 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 2d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Blueprint
The top-level skill owns every user-facing question. The two retained agents are optional, bounded, non-interactive finalizers that run only after the parent's accepted answers are durable.
{% include_shared "parent-owned-interview.md" %}
STATE-MACHINE
stateDiagram-v2
[*] --> detect
detect --> charter : charter_needs_work
detect --> prd : charter_complete
charter --> prd : charter_complete
prd --> [*] : prd_complete
On each phase transition, report with rp1 agent-tools emit using workflow blueprint, the generated {RUN_ID}, and the current state as --step. Derive RUN_NAME as Blueprint: {EFFECTIVE_PRD_NAME}. The first emit includes --name "{RUN_NAME}". Enter a non-terminal state with {"status":"running"}; finish prd with {"status":"completed"} and --close-run. On a fatal phase error, emit {"status":"failed"} for the current state before stopping.
Context
Use the pre-resolved projectRoot, kbRoot, and workRoot values from Workflow Bootstrap. They are authoritative and may point to different storage locations.
- Charter:
{kbRoot}/charter.md - PRD:
PRD_PATH, derived after name validation as{workRoot}/prds/{EFFECTIVE_PRD_NAME}.md - Charter template:
plugins/base/skills/artifact-templates/templates/charter-interviewer/charter.md - PRD template:
plugins/base/skills/artifact-templates/templates/blueprint-wizard/prd.md
Procedure
1. Validate The PRD Name Before Effects
Set EFFECTIVE_PRD_NAME = PRD_NAME || "main".
Validate EFFECTIVE_PRD_NAME against ^[A-Za-z0-9][A-Za-z0-9_-]*$. Use the value exactly as validated; do not trim, sanitize, or rewrite it. If it does not match, explain that the name must begin with an ASCII letter or number and contain only ASCII letters, numbers, _, or -, then stop. This validation MUST happen before any artifact read, artifact write, user question, or agent dispatch.
After successful validation:
- Set
PRD_PATH = {workRoot}/prds/{EFFECTIVE_PRD_NAME}.md. This is the sole writable PRD artifact path. - Emit
detectrunning. - Read
{kbRoot}/charter.mdto begin artifact-only detection.
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.
- 2d ago First seen · 244 lines · 19 tokens per session scan A f47b4a1691df
blueprint is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 3d ago), licensed Apache-2.0. It adds 19 tokens to every session and 2,954 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-07.
Other skills, from other repositories
dream
Batch-execute SHIP-ready wishes overnight — pick wishes, orchestrate workers, review PRs, wake up to results.
at-zentao
Handle ZenTao (禅道) Bugs and Tasks end to end, including updating or writing back an item after code changes, managing Task status and hours, and reading linked Stories. Use for referenced ZenTao items, requirements, status changes, time entries, or post-implementation synchronization.
openspec-bulk-apply-change
Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.
genie-orca-wish
Turn a brainstorm/design into an APPROVED-able wish whose Dispatch plan is the literal input to Orca tasks and Linear issues. High-reasoning pass: pre-decide everything so fast workers can execute without judgment calls.
honest-closeout
Close a task with a report a reviewer can trust — every acceptance line answered with evidence or a recorded blocking reason, human corrections credited to whoever made them, refuted hypotheses kept, background processes proven stopped, and the chat message copied verbatim from the report. Use when reporting work as…
close-the-gaps
Product Analyst session: fetches a ticket, loads project skills, explores affected code, asks gap-analysis questions one at a time, outputs Gherkin-format refined ticket. Use when refining a ticket before dev starts.