New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Comprehension Check

by NoobyGains in NoobyGains/godmode

A skill your agent uses when implementing any substantial feature, multi-file modification, or architectural change - produces a plain-language walkthrough of every alteration so the developer can…

MITAuto-check passedWriting & Content

Install Comprehension Check

skills CLI
$ npx skills add NoobyGains/godmode --skill comprehension-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NoobyGains/godmode comprehension-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NoobyGains/godmode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/comprehension-check .claude/skills/comprehension-check && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
comprehension-check
GitHub stars
107
Token cost
~1.5k tokens
SKILL.md length
489 words
Files
1
Skills in repo
34
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when implementing any substantial feature, multi-file modification, or architectural change - produces a plain-language walkthrough of every alteration so the developer can…

  • Works in 4 steps: Produce a Change Walkthrough → Deliver the Walkthrough → Obtain Explicit Confirmation → …
  • Implementing any substantial feature
  • SKILL.md covers Overview, The Prime Directive, When to Use and The Process, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Comprehension Check is an agent skill from NoobyGains/godmode. Use when implementing any substantial feature, multi-file modification, or architectural change - produces a plain-language walkthrough of every alteration so the developer can verify genuine understanding before committing, preventing the accumulation of cognitive debt where code ships faster than comprehension

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Plain language and style rules. The repository describes itself as: The AI development framework that thinks before it builds. 36 composable skills for Claude Code, Cursor, Codex, and OpenCode. The licence is MIT.

When your agent uses it

  • Implementing any substantial feature
  • Multi-file modification
  • Preventing the accumulation of cognitive debt where code ships faster than comprehension

Example prompts

  • “/comprehension-check”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Produce a Change Walkthrough
  2. Deliver the Walkthrough
  3. Obtain Explicit Confirmation
  4. Surface Unsolicited Changes

What it can do on your machine

Read from SKILL.md and the folder at commit 441103a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Comprehension Check loads about 1.5k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 489 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NoobyGains/godmode at commit 441103a, republished under its MIT licence (© NoobyGains). 489 words, ~1,468 tokens.

Download SKILL.mdSave it as .claude/skills/comprehension-check/SKILL.md (or your agent's skills folder).
name
comprehension-check
description
Use when implementing any substantial feature, multi-file modification, or architectural change - produces a plain-language walkthrough of every alteration so the developer can verify genuine understanding before committing, preventing the accumulation of cognitive debt where code ships faster than comprehension

Comprehension Check

Overview

AI produces code at a pace that outstrips human absorption. Shipping changes you cannot fully explain creates cognitive debt -- the inability to troubleshoot, extend, or reason about what was built.

Core principle: Comprehension precedes commitment. If you cannot articulate every modification in ordinary language, you have not earned the right to commit it.

The Prime Directive

NO COMMIT UNTIL EVERY CHANGE IS UNDERSTOOD

Before any AI-generated or AI-assisted code reaches version control, the developer must grasp what each change accomplishes and why it was implemented that way.

When to Use

Triggered after:

  • Any modification touching 3 or more files
  • Non-trivial algorithm or data-structure implementations
  • Structural shifts (new modules, altered data flow, dependency rewiring)
  • Security-adjacent code (authentication, encryption, input sanitization)
  • Autonomous agent decisions (changes you did not explicitly dictate)

Skippable for:

  • Single-character or typo corrections
  • Changes the developer dictated verbatim, line by line
  • Pure boilerplate generation (scaffolding configs, lockfiles)

The Process

Phase 1: Produce a Change Walkthrough

After implementation completes, before any commit occurs:

For EVERY modified file, articulate:

1. WHAT: What is different now? (Describe the meaning, not the diff)
2. WHY: What motivated this particular change?
3. CONTEXT: How does this change interact with the broader modification set?
4. HAZARD: What failure modes does this change introduce?
Phase 2: Deliver the Walkthrough

Structure the output as follows:

markdown
## Modification Walkthrough

### [path/to/first-file]
**What:** Introduced sliding-window rate limiting that counts requests per IP address.
**Why:** The login endpoint was exposed to brute-force enumeration.
**Context:** Middleware executes ahead of authentication routes; relies on Redis for distributed state.
**Hazard:** If Redis becomes unreachable, the limiter fails open (permits all traffic). Worth discussing: should it fail closed instead?

### [path/to/second-file]
**What:** Login handler now returns HTTP 429 when the rate limiter activates.
**Why:** The middleware flags rate-limited requests via `req.rateLimited`.
**Context:** Early exit occurs before password verification, which also blocks timing-based attacks.
**Hazard:** Negligible -- a simple conditional guard.

## Structural Consequences
- New runtime dependency: Redis (stores rate-limit counters)
- New middleware layer inserted between routing and handler execution
- Login request lifecycle now: rate-check -> authenticate -> respond

## Open Questions
1. Should the rate limiter deny all traffic when Redis is unavailable, or allow it?
2. Should rate limiting extend beyond authentication endpoints?
Phase 3: Obtain Explicit Confirmation

Ask directly: "Do you fully understand these changes and want to proceed with the commit?"

When the developer raises questions:

  • Resolve them thoroughly
  • Do not gloss over confusion
  • Lingering confusion equals accruing cognitive debt
Phase 4: Surface Unsolicited Changes

Whenever a change was not part of the original request:

HEADS UP: I additionally [modified X] because [rationale].
This was NOT part of your original instruction. Keep it or revert?

AI agents frequently make "helpful" supplementary changes. Every one must be disclosed.

Indicators of Genuine Comprehension

The developer should be able to:

  • Describe what each altered file does differently now
  • Justify why each alteration was necessary
  • Predict what would break if a specific change were rolled back
  • Enumerate any new dependencies or patterns that were introduced
  • Identify where to investigate if a bug surfaces in this code later
Show full SKILL.md (198 more words)Show less

Cognitive Traps

RationalizationTruth
"The test suite passes, so I trust it"Tests validate behavior, not understanding. You will debug this blind later.
"I will review it when things calm down"You will not. The context window closes the moment you move on.
"It is mostly boilerplate"A single incorrect line in boilerplate can open a security hole.
"I grasp the overall concept"High-level intuition collapses at debugging time. Specific comprehension is required.
"Deep review reduces my velocity"Deploying code you cannot explain reduces velocity far more when it fails.
"The AI is competent"AI generates plausible output. Plausible and correct are not the same thing.

Guardrails

Prohibited actions:

  • Committing AI-produced code without reading the walkthrough
  • Suppressing unsolicited-change disclosures
  • Rushing past developer confusion or uncertainty
  • Equating green tests with genuine comprehension

Required actions:

  • Generate walkthroughs for all multi-file modifications
  • Disclose every change that exceeded the original request
  • Collect explicit confirmation before committing
  • Fully resolve every developer question

Integration

Invoked after:

  • godmode:delegated-execution -- Review output from delegated agent implementations
  • godmode:test-first -- After code is written and tests pass
  • godmode:parallel-execution -- After merging results from parallel agent work

Invoked before:

  • godmode:completion-gate -- First understand, then verify
  • godmode:merge-protocol -- Understand before merging into the target branch

© NoobyGains, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/comprehension-check of NoobyGains/godmode.

Open the folder on GitHubat commit 441103a

Compare with similar skills

Comprehension Check next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Comprehension Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Comprehension Check this skillNoobyGains/godmode107—~1.5kAutomated safety check: PassMIT
Asd Ste100danyuchn/asd-ste100-skill4.2k—~4.1kAutomated safety check: PassMIT
Simple Issue Descriptionevery-app/open-seo23k1 repos~1.2kAutomated safety check: PassMIT
Ponytail AuditDietrichGebert/ponytail159k—~1.4kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins10k10 repos~2.4kAutomated safety check: PassNone
Natural Japanese Business Writingcoji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT

Similar skills

  • Asd Ste100

    danyuchn/asd-ste100-skill

    A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…

    4.2k GitHub stars~4.1k tokensUpdated 5 days ago
    Writing & ContentAuto-check passed

  • Simple Issue Description

    every-app/open-seo

    Turn a rough bug report, feature request, support note, or pull request into a short, plain-language issue focused on the problem and desired behavior.

    23k GitHub starsUsed in 1 repo~1.2k tokens
    Writing & ContentAuto-check passed

  • Ponytail Audit

    DietrichGebert/ponytail

    Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split.

    159k GitHub stars~1.4k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • Technical Writing Standard

    cursor/plugins

    Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    10k GitHub starsUsed in 10 repos~2.4k tokens
    Writing & ContentAuto-check passed

  • Natural Japanese Business Writing

    coji/natural-japanese

    Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

    1.9k GitHub stars~2.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Pgjev

    realZachi/pg-jev

    Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model).

    1.1k GitHub stars~2.9k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed

More from NoobyGains/godmode

All 34 skills in this repo

  • Activation

    NoobyGains/godmode

    A skill your agent uses when starting any conversation - establishes how to locate and invoke skills, mandating Skill tool usage before ANY response including clarifying questions

    107 GitHub stars~2.4k tokensUpdated 7 mo ago
    Auto-check passed

  • Agent Messaging

    NoobyGains/godmode

    A skill your agent uses when dispatching subagents, composing prompts for teammates, structuring handoff reports, or managing context boundaries between agents.

    107 GitHub stars~3k tokensUpdated 7 mo ago
    Auto-check passed

  • Codebase Research

    NoobyGains/godmode

    A skill your agent uses when building ANY feature within an existing project - search the current codebase for existing patterns, conventions, similar implementations, and established approaches…

    107 GitHub stars~3.2k tokensUpdated 7 mo ago
    Auto-check: notes

  • Completion Gate

    NoobyGains/godmode

    A skill your agent uses when about to declare work done, fixed, or passing, before committing or opening PRs - demands executing verification commands and reading their output before making any…

    107 GitHub stars~1.6k tokensUpdated 7 mo ago
    Auto-check passed

  • Delegated Execution

    NoobyGains/godmode

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    107 GitHub stars~2.4k tokensUpdated 7 mo ago
    Auto-check passed

  • Deployment Advisor

    NoobyGains/godmode

    A skill your agent uses when making technology, hosting, or infrastructure decisions — recommends services, databases, and deployment strategies based on project requirements and what the user…

    107 GitHub stars~4k tokensUpdated 7 mo ago
    Auto-check: notes

Categories

Questions about Comprehension Check

What does Comprehension Check do?

A skill your agent uses when implementing any substantial feature, multi-file modification, or architectural change - produces a plain-language walkthrough of every alteration so the developer can…. Comprehension Check is an agent skill from NoobyGains/godmode.

When should I use Comprehension Check?

Comprehension Check fits situations like: implementing any substantial feature; multi-file modification; preventing the accumulation of cognitive debt where code ships faster than comprehension.

How do I install Comprehension Check in Claude Code?

Run `npx skills add NoobyGains/godmode --skill comprehension-check -a claude-code`. Or copy the skill folder (skills/comprehension-check in NoobyGains/godmode) into .claude/skills/comprehension-check in your project. Claude Code loads it when a task matches its description.

How do I install Comprehension Check in Codex?

Run `npx skills add NoobyGains/godmode --skill comprehension-check -a codex`. Or copy the skill folder (skills/comprehension-check in NoobyGains/godmode) into .agents/skills/comprehension-check in your project. Codex loads it when a task matches its description.

Can I use Comprehension Check in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NoobyGains/godmode --skill comprehension-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comprehension-check, .gemini/skills/comprehension-check, .github/skills/comprehension-check and .opencode/skills/comprehension-check in your project.

What does Comprehension Check need to run?

SKILL.md names no scripts, command-line tools or credentials: Comprehension Check is instructions for the agent only.

Does Comprehension Check access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Comprehension Check safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Comprehension Check use?

Comprehension Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Comprehension Check use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Comprehension Check?

Skills that share tags, products or a category with Comprehension Check: Asd Ste100 (danyuchn/asd-ste100-skill, 4.2k stars), Simple Issue Description (every-app/open-seo, 23k stars), Ponytail Audit (DietrichGebert/ponytail, 159k stars) and Technical Writing Standard (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Comprehension Check?

NoobyGains (a GitHub user) maintains it in NoobyGains/godmode, which has 107 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on March 9, 2026.

Source: NoobyGains/godmode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.