learn

A workflow step for recording reusable lessons from a completed Hardproof run, where Hardproof is the surrounding process for checking and delivering engineering work. It links each lesson to evidence from that run or records why no lesson should be saved.

In plain words
What is it for?
Use it after a Hardproof run to capture supported lessons about decisions, corrections, review findings, risks, or remaining issues—or to document an intentional decision to save nothing.
Why use it?
It prevents useful project knowledge from being lost while avoiding unsupported generalizations, secrets, and private output. It keeps the decision about what to remember explicit.

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/learn
Any agent
npx skills add asimons81/hardproof --skill learn
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 288 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 $0.00288
Opus 5 $0.00013 $0.00144
Sonnet 5 $0.00005 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 2d ago against content hash a2e4b4f9a5d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn 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/learn/SKILL.md · 35 lines

What it actually says

Learn from the Run

Purpose

Decide deliberately whether completed work contains reusable project knowledge without silently changing user instructions or skills.

When to use

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

Inputs

Read decisions, corrections, review findings, evidence, remaining risks, and the completion report.

Procedure

  1. Identify lessons that are specific, reusable, and supported by the run.
  2. Exclude secrets, private output, transient failures, and guesses.
  3. Record a learning artifact with hardproof_record, including source-run provenance and intended scope.
  4. If nothing qualifies, record an explicit skip reason rather than inventing a lesson.
  5. Do not create or edit global knowledge automatically.

Required records

Standard and Critical require a learning artifact or explicit skip reason. Quick may skip with a recorded reason when its profile path requires one.

Exit criteria

The learning decision is durable, privacy-safe, and linked to evidence. Critical also has a human completion approval.

Failure modes

Do not persist credentials, raw private content, unsupported generalizations, or duplicate guidance. Leave proposals reviewable.

Verification

Confirm provenance and redaction, then call hardproof_transition for COMPLETE. Never declare completion only 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 a2e4b4f9a5d5

Subscribe to this mod's changes

learn is a skill published in the GitHub repository asimons81/hardproof (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 288 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

notebooklm

Full NotebookLM API via notebooklm-py CLI: create notebooks, add sources, generate podcasts, videos, infographics, slides, quizzes, flashcards, mind maps. Triggers on: "notebooklm", "create a podcast", "audio overview", "generate flashcards", "generate infographic", "/notebooklm".

Mathews-Tom/armory · 71 tokens

repo-readiness-audit

Use when a user asks whether an identified repository is ready for further development, release work, a new feature, handoff, or a new contributor, requiring a disciplined read-only audit before an evidence-backed verdict.

asimons81/hermes-field-kit · 48 tokens

refine

End-of-session reflection. Reviews friction encountered during the session and proposes updates to docs/ to capture lessons learned.

windmill-labs/windmill · 25 tokens

dont-lie-to-me

Use when the user explicitly wants evidence-disciplined answers that separate observed facts, sourced claims, user reports, inference, unknowns, and contradictions before making strong factual or completion claims.

asimons81/hermes-field-kit · 43 tokens

memory-onboarding

Guide someone new to Basic Memory through designing and building a complete personal knowledge system — interview them about what they want to track, propose a structure, build it with schemas and instruction notes, teach them to use it, and set up their AI assistant to load it automatically. Use this skill whenever a…

basicmachines-co/basic-memory · 148 tokens

x-analytics-import

Use when X Analytics CSV exports must be inspected, validated, normalized, imported, or compared through a repeatable private-by-default workflow.

asimons81/hermes-field-kit · 32 tokens