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 vosslab/vosslab-skills --skill blueprint-plan-draftergit clone --depth 1 https://github.com/vosslab/vosslab-skillsWrote 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/vosslab/vosslab-skills/blueprint-plan-drafter)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/blueprint-plan-drafter"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/blueprint-plan-drafter/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/vosslab/vosslab-skills/blueprint-plan-drafter"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/blueprint-plan-drafter.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 | $0.00038 | $0.01723 |
| Opus 5 | $0.00019 | $0.00861 |
| Sonnet 5 | $0.00008 | $0.00345 |
| Haiku 4.5 | $0.00004 | $0.00172 |
Grade A, and why
blueprint-plan-drafter 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 12d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blueprint plan drafter
Overview
Build an execution-ready plan with a stable core and a shape that fits the work.
Execution shape
- Match the plan structure to the work.
- Use
parallel-planfor genuine independent lanes. - Keep serial work in one lane.
- Apply the parallel-plan readiness checklist to multi-workstream milestones.
Terminology
Use the definitions and durable naming guidance in references/DEFINITIONS.md.
Authority and boundaries
- Read any repository files needed for planning context.
- Limit edits to documentation artifacts such as plans, progress trackers, changelog notes, and review notes.
- Coordinate work for multiple coders through clear ownership and handoff boundaries.
Planning stance
- Think forward-first and solution-oriented.
- Optimize for feasible execution and constructive decisions.
- Prefer a clean redesign when evidence shows the current design has failed.
- Keep ambition grounded by explicit acceptance gates and dependency-aware sequencing.
Evidence-led planning
- Use the scientific method for uncertain design choices: observe, hypothesize, test, compare, measure, and update the plan.
- Match each claim's certainty to the available evidence.
- Keep a proposed method open while a manager, subagent, or dedicated agent gathers the evidence needed to choose it.
- Base requirements and gates on observed behavior, representative inputs, and the intended improvement.
- Measure intentional improvements with justified tolerances, comparisons, automated evidence, or independent agent review.
- Give the manager and subagents a complete path through every gate using repository-appropriate evidence. Give subagent-produced changes an independent agent review.
Stabilization and redesign
- Assess whether the current system works reliably on its target inputs.
- When the root cause is uncertain, use a bounded stabilization plan:
- Each experiment follows the proof ladder: observed failure, suspected cause, single change, success metric, revert criteria.
- Keep one abstraction level per document: (a) root-cause debugging, (b) algorithm redesign, or (c) organizational program management.
- Use clean redesign when existing evidence invalidates the algorithm or architecture.
- Use stabilization evidence to choose between incremental repair and redesign.
- See scrap-vs-fix decision criteria in
references/plan_quality_standard.md.
What ships with it
7 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.
- 12d ago First seen · 161 lines · 38 tokens per session scan A 06f08d375f9d
blueprint-plan-drafter is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 38 tokens to every session and 1,723 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…