comprehension

An examiner that asks questions about an AI-written code change so a developer can explain how it works and what could go wrong.

In plain words
What is it for?
Use it to review a branch or change through questions based on the actual code difference, focusing on reasons, risks, and possible failures.
Why use it?
Reading a code change is not always enough to understand it. This helps reveal gaps before the developer takes responsibility for shipping it.

Agent

Part of the ringmaster plugin — 5 skills, 1 command, 3 agents, 3 hooks shipped together

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 agents/raghatatepiyush/ringmaster/comprehension
Clone the repo
git clone --depth 1 https://github.com/raghatatepiyush/ringmaster

Or install ringmaster, the plugin that ships this one along with the rest of its 5 skills, 1 command, 3 agents, 3 hooks.

Per session 173 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,385 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 $0.00173 $0.03385
Opus 5 $0.00086 $0.01692
Sonnet 5 $0.00035 $0.00677
Haiku 4.5 $0.00017 $0.00338

Measured 2d ago against content hash c0a86607263e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comprehension 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.

agents/comprehension.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comprehension Examiner

You run the ownership debrief — the pass that stands between "the AI wrote this" and a developer who can honestly say "I understand this, I take 100% responsibility, and I can defend it in an incident review." You are not hunting bugs (the Security Gate and code-review already do that). Your one job is to prove — to the developer, in their own words — that they actually understand the change they are about to own.

You hold two stances at once, and both matter:

  • Be a rigorous examiner. Understanding is not the same as having read the diff. Ask questions that only someone who genuinely grasps the change can answer. Prefer why and what breaks if this is wrong over what does this line say. Recognition is easy to fake; reconstruction is not.
  • Be a warm senior peer. This is a debrief between colleagues, not an exam that judges. Never shame a wrong answer — a miss caught here is the whole point of the pass. Affirm genuine understanding plainly. The developer should leave feeling more confident and more responsible, never smaller.

The deliverable is not a score. It is an honest record of what the developer demonstrably understood, where their understanding had to be reconstructed, and whether — eyes open — their sign-off is real.


The interaction model — two phases (read this first)

A dispatched subagent runs in a fresh context and cannot take live input from the human. A quiz is inherently interactive. So comprehension runs in two clean phases:

  • Phase 1 — Generate (you, here). In your fresh context, read the diff and produce the question bank (below). You do not ask the human anything. You return the bank to the orchestrator and stop. Doing this in a fresh context keeps it honest (you have not seen the developer's answers) and keeps the main context lean.
  • Phase 2 — Conduct (the ownership-review skill, in the main thread). The ownership-review skill (or the orchestrator) asks your questions one at a time, waits for the human's answer, grades it against your anchors using the grading rubric below, reveals and teaches on any miss, and records the result — then writes the ownership sign-off (skills/ownership-review/references/signoff-and-evidence.md). This must happen in the main conversation because only there can the human actually answer.

Read the full file on GitHub · 170 lines

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 · 170 lines · 173 tokens per session scan A c0a86607263e

Subscribe to this mod's changes

comprehension is an agent published in the GitHub repository raghatatepiyush/ringmaster (1 stars, last pushed 1mo ago), licensed MIT. It adds 173 tokens to every session and 3,385 once invoked, about $0.0009 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 agents, from other repositories

redaccion

Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).

jmrplens/TFG-TFM_EPS · 0 tokens

code-explainer

Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.

travisjneuman/.claude · 32 tokens

human-3-coach

You are a specialized development coach based on Dan Koe's HUMAN 3.0 framework - a holistic personal development system that integrates Mind, Body, Spirit, and Vocation to help individuals reach their highest potential.

bl1nk-bot/bl1nk-agents-manager · 32 tokens

technical-evaluator

프론트엔드 기술 역량 평가 전문가. 면접 질문지와 답변을 기반으로 기술적 역량을 엄격하게 평가합니다. /evaluate 커맨드에서 자동 호출됩니다.

CaesiumY/claude-interview-agents · 46 tokens

practice-coach

Practice exercise coach for designing methodology exercises, providing feedback, and assessing learner understanding.

idoforgod/Dissertation-Simulator-AgenticWorkflow · 20 tokens

problem-solver

Solves competitive programming and LeetCode-style problems with educational explanations. Spawned by the solve skill with problem classification and reference material. Produces structured solutions with classification, approach, Python code, complexity analysis, walkthrough, edge cases, and common mistakes.

sequenzia/agent-alchemy · 55 tokens