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 duthaho/skillhub --skill blueprintgit clone --depth 1 https://github.com/duthaho/skillhubWrote 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/duthaho/skillhub/blueprint)<a href="https://agentmods.dev/skills/duthaho/skillhub/blueprint"><img src="https://agentmods.dev/badge/skills/duthaho/skillhub/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/duthaho/skillhub/blueprint"><img src="https://agentmods.dev/badge/skills/duthaho/skillhub/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 | $0.00225 | $0.02489 |
| Opus 5.5 | $0.00090 | $0.00996 |
| Sonnet 5.5 | $0.00045 | $0.00498 |
| Haiku 4.5 | $0.00022 | $0.00249 |
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 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
blueprint — architecture the team can read, with receipts
/blueprint — whole-repo architecture doc + top-level mermaid diagram
/blueprint <module|feature> — scoped doc + diagram for one area
/blueprint refresh — regenerate only what the diff since the stamp touched
Answer one question: what does a person need to see to understand how this code is put together — and can every box and arrow be defended? The documented failure mode of AI-generated architecture docs is confident fiction: diagrams with components that don't exist and arrows nobody can trace. The countermeasure is structural, not stylistic — no edge without a locator, no mermaid the checklist didn't render, no write without a yes.
Step 0 — Scope, and respect what exists
Look before generating:
- Existing output? Check for
docs/blueprint/and itsmanifest.md. The explicit command wins: a scope argument runs SCOPED and/blueprint refreshruns REFRESH regardless. A bare/blueprintwith existing output defaults to REFRESH — read the manifest first and jump to the refresh path in Step 5; offer a full regenerate only if the user asks or the manifest looks obsolete. An existing hand-writtendocs/architecture*file is context to read and link, never to overwrite. Whichever mode wins, if the manifest's stamp trails HEAD, state the drift in one line — "blueprint is N commits behind (touched: X, Y)" viagit rev-list --count+git diff --statover<stamped-commit>..HEAD— and offer the refresh unless this run already is one. A stamp that no longer resolves (rebase, shallow clone) is itself the staleness signal: report it and offer a full regenerate. Staleness surfaces at every touch, not only on a remembered refresh. - Orient cheaply first. Read
AGENTS.md/CLAUDE.md/READMEif present (the map skill writes the first) — they answer in seconds what fan-out answers in minutes. No AGENTS.md in a large repo? Offer/mapfirst; its output makes this run better and the repo better oriented for every later agent. - Size the repo (
git ls-files | wc -l, top-level layout) to scale the fan-out: a small repo graphs in one pass inline; a large or polyglot one gets one Explore agent per area. - A scope argument (
/blueprint the payment flow) narrows everything to that module or feature: the graph, the doc, and the diagram cover that area and its direct boundaries — not the whole repo.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +5 lines c92d7d472389
- 1mo ago First seen · 182 lines · 225 tokens per session scan A 4afe83314351
blueprint is a skill published in the GitHub repository duthaho/skillhub (9 stars, last pushed 1mo ago), licensed MIT. It adds 225 tokens to every session and 2,489 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
chief-data-officer-advisor
Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehouse vs lakehouse vs mesh, build-vs-buy), B2B customer-data-as-asset valuation and M&A readiness, data team org evolution. Use when deciding whether to train models on customer data, choosing data…
vpe-advisor
VP of Engineering advisory for startups: delivery throughput (DORA 4 metrics + bottleneck identification), engineering hiring funnel (sourcing → screen → onsite → offer conversion + time-to-fill + pipeline gap), engineering team structure (squad/tribe/chapter design + tech-lead manager-trigger thresholds), and…
general-counsel-advisor
General Counsel advisory for startups: contract review (MSA, SaaS, NDA, DPA, employment), IP strategy, term sheet decoding, and regulatory landscape mapping. Use when reviewing any contract or term sheet, deciding when to engage outside counsel, defining IP strategy, evaluating regulatory exposure (HIPAA, GDPR, FDA…
strategic-alignment
Cascades strategy from boardroom to individual contributor. Detects and fixes misalignment between company goals and team execution. Covers strategy articulation, cascade mapping, orphan goal detection, silo identification, communication gap analysis, and realignment protocols. Use when teams are pulling in different…
board-meeting
Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated, no cross-pollination), critic analysis, synthesis, founder review, and decision extraction. Use when the user invokes /c-level-agents:boardroom, calls a…
wrap-up
Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says "wrap up", "close this out", "what do I own now", "give me the summary", "recap the agent", or when the orchestrator routes…