discover

A discovery process for understanding an engineering request and its current project context before designing a solution. It examines the repository, guidance, configuration, tests, documentation, constraints, and unknowns.

In plain words
What is it for?
Use it at the start of an engineering task to inspect relevant files and history, identify constraints and open questions, and document what is known before planning implementation.
Why use it?
It separates observed facts from assumptions and exposes missing information early. This helps keep the proposed work within scope and aligned with the project's actual behavior.

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

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 281 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 $0.00025 $0.00281
Opus 5 $0.00013 $0.00140
Sonnet 5 $0.00005 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured 2d ago against content hash 7023f4b4f481, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

discover 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/discover/SKILL.md · 35 lines

What it actually says

Discover the Work

Purpose

Establish what is true in the current workspace and what the request actually requires.

When to use

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

Inputs

Read the request, profile, repository state, applicable project guidance, prior run records, and inspected public interfaces.

Procedure

  1. Inspect relevant code, tests, configuration, history, and documentation.
  2. Separate observed facts from assumptions.
  3. Identify user-visible outcomes, compatibility constraints, security boundaries, and unresolved questions.
  4. Keep scope tied to the request; do not choose an implementation yet.
  5. Record the findings with hardproof_record as a discovery artifact.

Required records

Record inspected evidence, constraints, scope boundaries, and open questions. Standard and Critical profiles require a discovery artifact.

Exit criteria

Discovery is ready when the design can be evaluated against explicit facts and no blocking question is hidden.

Failure modes

Pause when required evidence is unavailable. Do not invent current behavior, private Hermes APIs, approvals, or external facts.

Verification

Recheck cited paths and commands against the current workspace, then call hardproof_transition for DESIGN. Never claim the stage changed in prose.

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 · 25 tokens per session scan A 7023f4b4f481

Subscribe to this mod's changes

discover is a skill published in the GitHub repository asimons81/hardproof (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 25 tokens to every session and 281 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