design

A design workflow for turning verified software-discovery findings into a small, reviewable technical solution before coding begins.

In plain words
What is it for?
Use it to define contracts and failure handling, compare approaches, record decisions, and prepare a design for human approval.
Why use it?
It makes behavior, interfaces, risks, alternatives, and rollback consequences clear before implementation starts.

Skill for Claude CodeCodex

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/asimons81/hardproof/design
Any agent
npx skills add asimons81/hardproof --skill design
Clone the repo
git clone --depth 1 https://github.com/asimons81/hardproof

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 284 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 $0.00023 $0.00284
Opus 5 $0.00012 $0.00142
Sonnet 5 $0.00005 $0.00057
Haiku 4.5 $0.00002 $0.00028

Measured 2d ago against content hash cf88698077f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design 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.

hardproof/skills/design/SKILL.md · 35 lines

What it actually says

Shape the Design

Purpose

Convert verified discovery into a coherent solution whose consequences can be reviewed before product code changes.

When to use

Use for the DESIGN stage selected by the active run context.

Inputs

Use the approved request boundary, discovery artifact, current interfaces, profile requirements, and recorded risks.

Procedure

  1. State the intended behavior and excluded scope.
  2. Define public contracts, data ownership, trust boundaries, failure behavior, and rollback implications.
  3. Compare viable alternatives and choose the smallest reversible option.
  4. Record consequential choices with hardproof_record as decisions.
  5. Write the design artifact with hardproof_record.

Required records

Standard and Critical runs require a design artifact and a separate human design approval. Model tools cannot create that approval.

Exit criteria

The design is testable, compatible with inspected APIs, explicit about risks, and ready for human review.

Failure modes

Return to DISCOVERY when essential facts are missing. Pause if a safe boundary cannot be designed. Do not weaken gates to fit an attractive approach.

Verification

Cross-check every interface claim and unresolved risk, then ask the human to use /hardproof approve design. After approval exists, call hardproof_transition for PLAN.

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. 2d ago First seen · 35 lines · 23 tokens per session scan A cf88698077f4

Subscribe to this mod's changes

design is a skill published in the GitHub repository asimons81/hardproof (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 23 tokens to every session and 284 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 2026-08-31.

Related

Other skills, from other repositories

manuscript-typography

Audit academic manuscripts for typographic design conventions: booktabs table style, caption placement, dashes/quotes, units and numbers, cross-reference style, page layout, typographic hierarchy, professional polish. Triggers on: "check typography", "fix formatting", "polish my paper", "check my LaTeX", "typographic…

Mathews-Tom/armory · 107 tokens

architecture-reviewer

Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports. Triggers on: "review architecture", "critique design", "audit system", "assess scalability", "enterprise readiness", "technical due diligence". NOT for diagrams, use…

Mathews-Tom/armory · 71 tokens

concept-to-video

Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition. Triggers on: "create a video", "animate this", "make an explainer", "manim animation", "motion graphic". NOT for React video, use remotion-video.

Mathews-Tom/armory · 70 tokens

linkedin-post-style

Writes LinkedIn posts in a direct, analytical, dry-humored technical voice with visual companion guidance. Triggers on: "write this in my style", "draft a post", "rewrite this for LinkedIn", "post about this", "how should I phrase this".

Mathews-Tom/armory · 60 tokens

manuscript-provenance

Computational provenance audit verifying every number, table, and figure in a manuscript derives from code, not manual entry. Triggers on: "check provenance", "verify reproducibility", "audit my pipeline", "are my numbers from code", "provenance audit". Companion to manuscript-review (prose audit).

Mathews-Tom/armory · 70 tokens

manuscript-review

Pre-publication manuscript audit producing a section-level refactoring report with citation hygiene and submission-readiness checks. Triggers on: "review my paper", "check before submission", "is this ready to submit", "pre-pub checklist", "refactor my paper", "check my references", "does the abstract work".

Mathews-Tom/armory · 70 tokens