check-my-work

check-my-work is a skill for Claude Code, Codex from tomthebearded/guide-forge. It costs 188 tokens per session (705 once invoked), scanned A, original, MIT.

A read-only checker that compares a real project with the step-by-step guide used to build it. It reads milestone checkpoints and compares their expected complete files with the project's files, while ignoring cosmetic differences.

In plain words
What is it for?
Use it to verify tutorial-based builds, inspect which files were changed in version control, run available checks, and compare the results with expected checkpoint output.
Why use it?
It finds cases where a build step was skipped, changed incorrectly, or never completed, without modifying the project or guide.

Skill for Claude CodeCodex

Part of the guide-forge plugin — 14 skills 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 skills/tomthebearded/guide-forge/check-my-work
Any agent
npx skills add tomthebearded/guide-forge --skill check-my-work
Clone the repo
git clone --depth 1 https://github.com/tomthebearded/guide-forge

Made for: Claude Code, Codex.

Or install guide-forge, the plugin that ships this one along with the rest of its 14 skills.

Wrote 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.

agentmods badge for check-my-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomthebearded/guide-forge/check-my-work.svg)](https://agentmods.dev/skills/tomthebearded/guide-forge/check-my-work)
Your own site
<a href="https://agentmods.dev/skills/tomthebearded/guide-forge/check-my-work"><img src="https://agentmods.dev/badge/skills/tomthebearded/guide-forge/check-my-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 705 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 $0.00188 $0.00705
Opus 5 $0.00094 $0.00352
Sonnet 5 $0.00038 $0.00141
Haiku 4.5 $0.00019 $0.00071

Measured 5d ago against content hash aa18aebec7f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check-my-work 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 5d 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/check-my-work/SKILL.md · 48 lines

What it actually says

Skill: check-my-work

The complete, canonical contract for this skill is the paste-prompt it wraps, inlined here — follow it in full:

!cat "${CLAUDE_SKILL_DIR}/prompt.md"

(If the block above came back empty or errored, read prompt.md in this skill folder — it sits beside this SKILL.md — and follow that.)

As you follow it, adapt for the fact that you're a Claude Code skill, not a pasted prompt:

  • You're already invoked — skip its "How to use / paste this" preamble. The scope to check is $ARGUMENTS below (plus any attached files). Read the guide's guide/ files and the project's real files yourself rather than asking for them to be pasted.
  • You have tools here, so use the two the prompt leans on: read version control directly (which commits touched which files, and when) to answer was this step ever performed; and actually run the gate checks that need no human, then diff their output against the expected output the gate prints.
  • Read-only, on both sides. Do not edit the project, and do not edit any guide file — including progress.md and status.md. If the check ends in something that must be written, name the sibling skill that owns it: /mark-progress (the ledger), /report-issue (a guide defect), /amend-guide (a deliberate deviation that should become the plan), /log-feedback (friction worth recording).
  • When the reader asked to mark a run of steps or a whole milestone, check first and hand the confirmed result to /mark-progress — a single step just finished doesn't need this skill at all.

Scope to check / args:

$ARGUMENTS

Gate: report only what you actually verified. A check you couldn't run is unrun, never passed; a difference you can't tell apart from a rename is cosmetic, not a finding; and a milestone is never called verified here, because you did not watch its gate — you re-ran the half of it a machine can.

Files

What ships with it

1 file 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. 5d ago First seen · 48 lines · 188 tokens per session scan A aa18aebec7f6

Subscribe to this mod's changes

check-my-work is a skill published in the GitHub repository tomthebearded/guide-forge (3 stars, last pushed 4d ago), licensed MIT. It adds 188 tokens to every session and 705 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 skills, from other repositories

feedback

Guide the user to open a feedback issue for the simple-output-styles plugin. Use when the user wants to report feedback on an output style, the evals, the documentation, the installation, licensing, or wants to request a new style. Gathers the Claude Code version and the active style, then prepares a prefilled GitHub…

stefanobaghino/simple-output-styles · 72 tokens

pick

Help the user pick an output style from the simple-output-styles plugin and set it globally. Recommends actionable-clarity, or walks through the full list with the pros and cons of each style.

stefanobaghino/simple-output-styles · 44 tokens

diataxis

Classify, create, review, and maintain documentation using the Diátaxis framework — the four-quadrant system (tutorials, how-to guides, reference, explanation) that separates documentation by user need. Use this skill whenever the user wants to classify documentation into quadrants, perform a documentation gap…

zircote-plugins/documentation-review · 212 tokens

api-documentation

Patterns and templates for creating comprehensive API documentation using OpenAPI/Swagger, AsyncAPI, and manual documentation approaches. Use this skill whenever the user wants to document REST endpoints, generate or improve an OpenAPI spec, create Swagger docs, document WebSocket/event-driven APIs with AsyncAPI…

zircote-plugins/documentation-review · 163 tokens

changelog

Generate, update, review, and maintain changelogs using Keep a Changelog format, semantic-release, and conventional commits. Use this skill whenever the user wants to add a changelog entry, prepare release notes, document version changes, generate a changelog from git history, configure semantic-release, understand…

zircote-plugins/documentation-review · 164 tokens

documentation-standards

Standards and patterns for creating, reviewing, and improving technical documentation — covering markdown formatting, heading hierarchy, code blocks, links, writing style, accessibility, and language-native doc toolchains (rustdoc, godoc, Sphinx, TypeDoc, Javadoc, DocC, ExDoc). Use this skill whenever the user wants…

zircote-plugins/documentation-review · 207 tokens