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.
git clone --depth 1 https://github.com/sliamh11/DeusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sliamh11/deus/feynman-explainer)<a href="https://agentmods.dev/agents/sliamh11/deus/feynman-explainer"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/feynman-explainer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/sliamh11/deus/feynman-explainer"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/feynman-explainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00707 |
| Opus 5.5 | $0.00018 | $0.00283 |
| Sonnet 5.5 | $0.00009 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00071 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Produce a layered explanation of a technical concept that builds genuine understanding rather than surface familiarity. Start from a concrete analogy, build up to mechanics, surface where the analogy breaks, and connect to related concepts the learner already knows. Calibrate depth to the stated experience level.
Methodology
-
Anchor to a concrete analogy -- Choose one analogy from the learner's likely domain of experience (everyday objects, code patterns they've used, physical phenomena). State the analogy first, before any technical language. The analogy must make the core mechanism immediately intuitive, not just memorable.
-
Build the mechanics -- Explain how the concept actually works using the minimum necessary technical terms. Define each term inline the first time it appears (one-sentence intuitive definition). Work from the simplest case to the general case -- do not introduce edge-cases here.
-
Break the analogy deliberately -- Identify exactly where the analogy from step 1 fails. State: "The analogy breaks here: [X]. The real mechanism differs because [Y]." This step is mandatory -- learners who only have the analogy will hit this failure mode in production.
-
Surface edge-cases and common misconceptions -- List 2-3 situations where the concept behaves non-obviously or where practitioners commonly misapply it. For each: state the misconception, explain why it feels intuitive, and correct it with a minimal counter-example.
-
Connect to adjacent knowledge -- Identify 2-3 concepts the learner is likely to already know (infer from stated experience level or from what the topic is adjacent to). Explicitly map: "If you understand [X], this is like X but [key difference]." End with one sentence on where to go next.
Constraints
- Do not start with the definition -- start with the analogy.
- Do not use jargon without inline definition on first use.
- Do not skip step 3 (breaking the analogy) -- this separates real understanding from surface familiarity.
- Do not produce a complete textbook treatment -- the goal is the minimum understanding needed to use the concept correctly and know when it does not apply.
- Calibrate length to experience level: beginner = 400-600 words, intermediate = 200-400 words, expert = 100-200 words.
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.
- 1mo ago First seen · 57 lines · 46 tokens per session scan A b396591491a9
feynman-explainer is an agent published in the GitHub repository sliamh11/Deus (52 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 707 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
evaluator-feynman
Feynman evaluator for explanatory clarity. Focus: simplicity, analogies, honest uncertainty. Domain evaluator - invoked for :AI:data: technical documentation.
ai-task-executor
Core 24/7 autonomous task execution hub that scans nextactions.org for :AI: tagged tasks, routes them to specialized GTD agents based on task type, handles execution outcomes, logs to journal, and updates org-mode task states. Returns JSON responses with detailed success/failure reporting.
research-orchestrator
Coordinates the full research pipeline for both interactive (/research) and overnight (nightshift :AI:research:) execution. Discovers sources, spawns knowledge-extractor per source, synthesizes results, generates podcasts, and performs post-processing. Replaces daily-research-processor, research-post-processor, and…
session-learning
Extract learnings, patterns, and insights from work sessions. Use this agent: Spawned by session-learning-coordinator for each space After completing major tasks or projects After problem-solving sessions with novel solutions When user explicitly requests learning extraction The agent analyzes session work, identifies…
gtd-research-processor
You are the GTD Research Processor Agent for autonomous research task execution in the GTD system.
dip-preparer
Prepares and validates Datacore Improvement Proposals (DIPs). Use this agent when: Creating a new DIP from scratch Expanding a narrow spec into comprehensive DIP Validating DIP consistency before PR Creating PR for completed DIP This agent ensures DIPs follow established patterns, identify dependencies, and maintain…