blueprint

blueprint is a skill for Claude Code, Codex from sandsower/beislid. It costs 127 tokens per session (2,615 once invoked), scanned A, original, MIT.

A design skill that turns known requirements into an approved implementation approach before code is written. It identifies affected files, modules, data flow, and tests; it does not decide what the product should do.

In plain words
What is it for?
It is for designing features, planning how they should be built, and documenting the implementation structure before using the implementation workflow.
Why use it?
It prevents coding from starting before the behavior and technical approach are understood and agreed upon.

Skill for Claude CodeCodex

Part of the beislid plugin — 22 skills shipped together

Install

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.

agentmods
npx agentmods add skills/sandsower/beislid/blueprint
Any agent
npx skills add sandsower/beislid --skill blueprint
Clone the repo
git clone --depth 1 https://github.com/sandsower/beislid

Made for: Claude Code, Codex.

Or install beislid, the plugin that ships this one along with the rest of its 22 skills.

Wrote 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.

agentmods badge for blueprint

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandsower/beislid/blueprint.svg)](https://agentmods.dev/skills/sandsower/beislid/blueprint)
Your own site
<a href="https://agentmods.dev/skills/sandsower/beislid/blueprint"><img src="https://agentmods.dev/badge/skills/sandsower/beislid/blueprint.svg" alt="Measured on agentmods" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,615 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00127 $0.02615
Opus 5 $0.00063 $0.01307
Sonnet 5 $0.00025 $0.00523
Haiku 4.5 $0.00013 $0.00262

Measured 4d ago against content hash bc820c2f7a43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

skills/blueprint/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Blueprint

No code until the implementation design is approved. blueprint turns a clear ticket/spec/phase into an implementation approach. It does not decide what product should exist; spec does that.

Use this when:

  • Desired behavior is known
  • You need to choose an implementation approach
  • You need to identify files/modules/data flow/tests
  • A spec, approved Work Contract, or break-spec phase is ready for implementation design

Do not use this when:

  • The problem, user/workflow, or success criteria are unclear — route to spec
  • scope_classification.kind is multi_slice, project, or unknown without an approved selected phase/slice — route to break-spec or spec refinement as appropriate

If the repo declares custom lifecycle hooks, read ../lifecycle-hooks.md and honor any phase-boundary hooks before and after blueprint.

When beislid:agent_isolation is configured, design discussion remains read-only, but before the first repo artifact write load ../implement/workspace-placement-protocol.md plus the current host adapter and run ensure_orchestrator_workspace. Require a clean source and acknowledged destination for a requested top-level transition; stop with manual-transition-required before lifecycle writes when the host cannot prove it.

Process

  1. Load context — if the handoff includes an explicit Work Contract, spec/PRD, or phase artifact path, read it as your primary input. Otherwise, if the matching spec_approved or break_spec_approved latest pointer entry for the current ticket/branch resolves to a readable artifact, read that artifact as your primary input; if not, use the workflow-configured artifact path template when present, then if a handoff artifact exists in plans/ (Work Contract, spec, PRD, phase structure), read it as your primary input. Otherwise, check relevant files, docs, recent commits. Optional visual routing: only when repo-level beislid:visual_surfaces config exists and the effective blueprint mode is active, load visual-surface-protocol.md; it mirrors canonical .beislid/visual-surface-protocol.md for copied installs.
  2. Requirements check — if product behavior or acceptance criteria are unclear, stop and route to spec with the missing questions. When a Work Contract is present, proceed only when Status is approved; route draft or needs-human-decision back to spec. Treat unknowns as blocking when they affect implementation approach or acceptance criteria. Verify scope_classification has the seven #56 keys (kind, confidence, rationale, recommended_route, requires_human_approval, requires_split, split_reason), proof_requirements is a list (possibly empty), and reserved slots still match defaults (slice_plan: null, children: []) unless later tickets explicitly populated them. Broad/project work should not jump directly to scaffolding by default. Do not patch over vague requirements with implementation guesses.
  3. Scope check — use scope_classification when present. atomic and single_pr may proceed. multi_slice must route to break-spec unless a selected phase/slice is already provided. project must route to spec refinement/project boundary approval first in P0, then slice planning; do not scaffold by default. unknown or low-confidence high-consequence classifications route back to spec for refinement.
  4. Ask implementation questions one at a time — prefer multiple choice. Focus on architecture, data flow, boundaries, edge cases, and tests.
  5. Propose 2–3 implementation approaches — include trade-offs and your recommendation. Lead with the recommended option and say why.
  6. Present the design — scale to complexity. A few sentences for simple changes, detailed sections for complex ones. Get approval section by section, but keep progress prose context-only and ask the blocking question only once in the final response. Offer the stress-test option only as a final-response action when appropriate; choosing it invokes poke-holes. Optional Lavish design surface: if Step 1 found active beislid:visual_surfaces routing, apply visual-surface-protocol.md at this approval/choice/revision boundary when a visual plan, comparison, architecture/data-flow diagram, option table, or risk/test matrix materially improves understanding. Keep small/linear designs Markdown-first, but for large changes comparable to work that benefits from walk-the-diff, lean toward suggesting or prompting for the surface rather than skipping it. Respect suggest/prompt/auto exactly; absent config or off must not mention or invoke Lavish. Use the protocol's plan, comparison, diagram, and input guidance with a typed BEISLID_VISUAL_FEEDBACK_V1 gate for workflow: blueprint, action approve_revise_or_choose_blueprint, and decisions approve, revise, or choose (choose requires selected_option). Copy accepted visual approvals, revisions, or choices into the canonical Markdown/chat design record before proceeding; visual controls never bypass explicit blueprint approval before implement.
  7. Run blueprint_approved lifecycle actions - after the design is approved and any configured orchestrator placement gate passes, execute configured artifact and CLI lifecycle actions for the approved design. Do not auto-write design files or run ad-hoc side effects outside this lifecycle behavior in configured repos.
  8. Transition — normally invoke implement to create the implementation plan and include any lifecycle status/path. If invoked by kickoff, return the approved design plus lifecycle status/path to kickoff instead; kickoff must record discoveries and update the ticket first.

Read the full file on GitHub · 94 lines

Files

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.

Changes

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.

  1. 4d ago First seen · 94 lines · 127 tokens per session scan A bc820c2f7a43

Subscribe to this mod's changes

blueprint is a skill published in the GitHub repository sandsower/beislid (10 stars, last pushed 4d ago), licensed MIT. It adds 127 tokens to every session and 2,615 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens