feynman-explainer

A teaching check that reviews how well someone can explain a concept in their own words. It looks for unclear wording, missing assumptions, and gaps that would prevent another person from understanding or applying the idea.

In plain words
What is it for?
Use it after a learner submits a summary, says they understand, or prepares to explain something to a stakeholder. It asks for a revised explanation and can provide a compact model answer if needed.
Why use it?
It helps distinguish recognising an explanation from being able to communicate the concept clearly. The feedback focuses on the smallest important gaps instead of overwhelming the learner.

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/grcengineering/companion/feynman-explainer
Any agent
npx skills add grcengineering/companion --skill feynman-explainer
Clone the repo
git clone --depth 1 https://github.com/grcengineering/companion

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 514 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 $0.00062 $0.00514
Opus 5 $0.00031 $0.00257
Sonnet 5 $0.00012 $0.00103
Haiku 4.5 $0.00006 $0.00051

Measured 2d ago against content hash 0ed0e9ece965, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feynman-explainer 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.

skills/feynman-explainer/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

feynman-explainer

What

Ask the learner to teach a concept back, then identify the smallest gaps that block clear transfer.

When

  • The learner says they understand and wants to check.
  • The learner submits their own explanation or summary.
  • The learner is preparing to explain a concept to a stakeholder.
  • Another skill needs proof that the learner can transfer the concept.

Not For

  • First-pass concept teaching. Use concept-tutor.
  • Memory drills without a full explanation. Use recall-quiz.
  • Judging a live operational outcome.

Inputs

  • Learner-authored explanation.
  • Target audience, if known.
  • Intended concept or scenario.

Steps

  1. Ask the learner to explain the concept to a non-technical stakeholder.
  2. Grade clarity, missing assumptions, and transferability.
  3. Quote or paraphrase the strongest part.
  4. Name one gap and why it matters.
  5. Ask for a revised explanation.
  6. If needed, provide a compact model answer after the retry.

Validation

  • The revised explanation is simpler, more accurate, and transferable.
  • Feedback names one or two gaps, not a long list.
  • The learner does the rewrite before receiving the polished answer.

Gotchas

  • If the learner has not supplied an explanation, ask for one before grading.
  • If the explanation is audience-mismatched, calibrate to the intended listener.
  • If the learner asks for "the answer", run one explain-back attempt first unless they are blocked.

Failure Modes

  • Rewriting too early: preserve the learner's ownership of the explanation.
  • Over-grading: focus on the gap that changes understanding most.
  • Operational grading: evaluate the explanation, not the learner's organization.

Examples

  • User says "I think evidence freshness means recent proof" -> Grade what is right, name the missing fitness-for-purpose piece, and ask for a revised version.
  • User pastes a stakeholder explanation -> Score clarity, assumptions, and transfer, then ask for a tighter rewrite.
  • User asks "Explain this to me" -> Route to concept-tutor because they are not teaching it back yet.

Read the full file on GitHub · 63 lines

Files

What ships with it

3 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. 2d ago First seen · 63 lines · 62 tokens per session scan A 0ed0e9ece965

Subscribe to this mod's changes

feynman-explainer is a skill published in the GitHub repository grcengineering/companion (32 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 514 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

control-mapping

Maps NIST controls to FedRAMP requirements and documents. Use when helping with control implementation, compliance mapping, security baseline alignment, or understanding control requirements.

hackIDLE/fedramp-docs-mcp · 35 tokens

frmr-analysis

Analyzes FedRAMP FRMR documents to extract control mappings, KSI entries, and version changes. Use when the user asks about FedRAMP requirements, control mappings, compliance data, or needs to understand FRMR document content.

hackIDLE/fedramp-docs-mcp · 51 tokens

GRC & Compliance

Governance, risk, and compliance — risk assessment and scoring, control mapping across NIST CSF 2.0 / ISO 27001:2022 / SOC 2 / CIS Controls v8, gap analysis, audit evidence preparation, and security policy generation.

Masriyan/Claude-Code-CyberSecurity-Skill · 58 tokens

mapping-builder

Build a reviewed crosswalk (RequirementMappingSet YAML library + review xlsx/csv) between two CISO Assistant framework YAML files using Claude itself as the reasoning engine. Zero infrastructure — stdlib + pyyaml only, no embedders, no LM Studio, no Qdrant. Use when the user asks to map / crosswalk / generate a…

intuitem/ciso-assistant-community · 164 tokens

reference-controls-enricher

Enrich a CISO Assistant framework YAML by linking each assessable requirement to reference control URNs from the central doc-pol library (CISO Assistant Key Reference Controls). Produces a reviewable xlsx and patches the framework YAML in place. Use when the user asks to "add reference controls to framework X", "link…

intuitem/ciso-assistant-community · 102 tokens

ciso-assistant-basic-risk-assessment

Guide users through a basic risk assessment workflow in CISO Assistant, from asset identification to scenario creation. Use when: (1) User wants to start a risk assessment from scratch (2) User mentions "risk assessment", "identify risks", "threat scenarios", or "risk register" (3) User asks about qualitative vs…

intuitem/ciso-assistant-community · 138 tokens