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 agentmods add skills/asimons81/hardproof/discovernpx skills add asimons81/hardproof --skill discovergit clone --depth 1 https://github.com/asimons81/hardproofWhat 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 | $0.00025 | $0.00281 |
| Opus 5 | $0.00013 | $0.00140 |
| Sonnet 5 | $0.00005 | $0.00056 |
| Haiku 4.5 | $0.00003 | $0.00028 |
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.
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
- Inspect relevant code, tests, configuration, history, and documentation.
- Separate observed facts from assumptions.
- Identify user-visible outcomes, compatibility constraints, security boundaries, and unresolved questions.
- Keep scope tied to the request; do not choose an implementation yet.
- Record the findings with
hardproof_recordas 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.
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.
- 2d ago First seen · 35 lines · 25 tokens per session scan A 7023f4b4f481
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.
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…
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…
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.
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".
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).
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".