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 nanparth/ai-skill-hub --skill tech-blueprintinggit clone --depth 1 https://github.com/nanparth/ai-skill-hubWrote 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/nanparth/ai-skill-hub/tech-blueprinting)<a href="https://agentmods.dev/skills/nanparth/ai-skill-hub/tech-blueprinting"><img src="https://agentmods.dev/badge/skills/nanparth/ai-skill-hub/tech-blueprinting/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/nanparth/ai-skill-hub/tech-blueprinting"><img src="https://agentmods.dev/badge/skills/nanparth/ai-skill-hub/tech-blueprinting.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 | $0.00107 | $0.01448 |
| Opus 5.5 | $0.00043 | $0.00579 |
| Sonnet 5.5 | $0.00021 | $0.00290 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
tech-blueprinting 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⛔ GATE DISCIPLINE: host user-choice mechanism gates = hard stops. Never skip or auto-pick answer. Tool unavailable → numbered-text fallback → stop, wait for reply. No flag bypasses a gate; override flags pass only as user's recorded gate answer.
/tech-blueprinting
Release version: 2.0.0
Ground decisions and produce a reviewable brief. Default: ground → material decisions → brief → risk/contract review → handoff. Section collaboration is optional, not the default production line.
Routing
| Intent | Route |
|---|---|
| README, usage docs, document a skill | workflows/readme-write.md, preserve Part A/B/C and source-fidelity checks |
| Grill, stress-test, attack a plan, adjudicate external findings | workflows/grill.md, explicit request only |
| Implementation/dev plan | Default below plus references/plan-template.md |
| Spec, PRD, RFC, decision or architecture document | Default below; implementation-only fields only when feeding code work |
Ambiguous deliverable → a structured choice prompt ⛔ BLOCKING: README (Recommended) / General technical document. Fallback: numbered options in plain text; stop and wait.
Default workflow
- Ground ⛔ BLOCKING. Load shared doctrine and runtime adapter. Read supplied sources and existing document before editing; count lines before full reads. Establish audience, goal, impact, non-goals, destination and authority from existing context. Ask only for missing material context. Implementation docs: inspect scoped repo structure, commands, patterns, contracts, history and reuse before proposing architecture, using
references/context-gathering-details.md. - Material decisions ⛔ BLOCKING. Present grounded findings and consequential alternatives, not a fixed brainstorm quota. Record binding constraints versus provisional approach and reference examples. Invoke a structured choice prompt: Approve direction (Recommended) / Adjust direction / Add context. Fallback: numbered options in plain text; stop and wait. Existing explicit authorization covering this direction resolves the gate: cite its source and scope, do not re-ask. Missing material decisions or changed authority still require the gate; silence or inferred intent never answers it. Default to brief drafting, not a mandatory collaboration question. If user requests a choice of collaboration mode, a structured choice prompt: Draft brief (Recommended) / Collaborate by section. Fallback: numbered options in plain text; stop and wait. Explicit section collaboration loads
workflows/section-drafting-loop.md. - Draft brief. Cover problem, goal/non-goals, material decisions and rationale, contract boundaries, outcomes/proof, dependencies, owners and open risks. Implementation briefs use milestone contracts plus
references/implementation-doc-requirements.md; no mandatory code-filled microsteps. Preserve approved exact content. Output: general Markdown written directly (or via a dedicated notes skill if installed), Word through a dedicated docx skill if installed; README route writes directly under its own workflow. Default general output a user-selected output path (e.g../outputs/). Scratch-only scope stays scratch; no durable save implied. - Risk/contract review ⛔ BLOCKING. Dispatch independent
agents/spec-reviewer.mdwithdoc_pathonly; resolve blocking defects. Dispatch freshagents/reader-tester.mdwithdoc_content,test_questions,check_mode="full", no conversation. Questions test what to build, what remains local choice, proof, failure boundaries and escalation. No independent reviewer available → report incomplete review, do not simulate independence. Revise affected sections, then rerun affected checks. Grill stays optional via its route, never silently substituted for these reviews. - Handoff ⛔ BLOCKING. Present brief, review evidence, unresolved decisions and exact destination. Existing explicit authorization covering delivery to that destination resolves this conversational handoff: cite source/scope and deliver without re-asking. Otherwise a structured choice prompt: Done (Recommended) / One more review. Fallback: numbered options in plain text; stop and wait. Present a visible reviewable artifact and concise decision digest before any unresolved gate; no mandatory separate-turn choreography in this default workflow. Missing material decisions, destination/save authority and publication-owner gates still block their dependent actions. Ready means material blockers resolved, not every local step prewritten. Offer
/tech-implement <path>unless explicitly authorized implementation is already the next action; document approval alone is not permission to implement, commit or publish.
What ships with it
27 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.
- agents/grill-adjudicator.md 1.9 KB
- agents/grill-reviewer.md 2.5 KB
- agents/reader-tester.md 3.6 KB
- agents/spec-reviewer.md 2.0 KB
- PORTABILITY.md 3.3 KB
- references/context-gathering-details.md 1.2 KB
- references/guidance-notes.md 835 B
- references/implementation-doc-requirements.md 1.2 KB
- references/plan-template.md 3.6 KB
- references/readme-self-review.md 2.6 KB
- references/readme-template.md 4.7 KB
- references/runtime-adapter.md 344 B
- scripts/frame-template.html 7.4 KB
- scripts/helper.js 4.8 KB runs code
- scripts/server.cjs 16 KB runs code
- scripts/start-server.sh 6.2 KB runs code
- scripts/stop-server.sh 4.1 KB runs code
- shared/code-organization.md 6.6 KB
- shared/technical-delivery-doctrine.md 9.5 KB
- shared/technical-delivery-runtime-adapter.md 6.3 KB
- shared/technical-delivery-test-level.md 3.4 KB
- shared/test-level-protocol.md 3.4 KB
- tech-blueprinting-readme.md 5.4 KB
- workflows/grill.md 5.6 KB
- workflows/readme-write.md 7.4 KB
- workflows/section-drafting-loop.md 1.5 KB
- workflows/visual-companion.md 15 KB
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 · -49 lines · +22 tokens per session c689bf312b62
- 1mo ago First seen · 106 lines · 85 tokens per session scan A 6cb33465fa0b
tech-blueprinting is a skill published in the GitHub repository nanparth/ai-skill-hub (23 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 1,448 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…