verify-understanding

verify-understanding is a skill for Claude Code, Codex from eai-org/agent-toolkit. It costs 44 tokens per session (499 once invoked), scanned A, original, MIT.

A guided conversation that checks whether an engineer understands a feature before implementation begins. The engineer explains the feature in their own words using a ticket review document, and the agent corrects gaps from the available requirements.

In plain words
What is it for?
Use it to review who uses a feature, what they do, why it exists, and how its tickets fit together before development.
Why use it?
It exposes misunderstandings before coding starts, when they are easier to fix.

Skill for Claude CodeCodex

Part of the agent-toolkit plugin — 22 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/eai-org/agent-toolkit/verify-understanding
Any agent
npx skills add eai-org/agent-toolkit --skill verify-understanding
Clone the repo
git clone --depth 1 https://github.com/eai-org/agent-toolkit

Made for: Claude Code, Codex.

Or install agent-toolkit, the plugin that ships this one along with the rest of its 22 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 verify-understanding

README.md
[![agentmods](https://agentmods.dev/badge/skills/eai-org/agent-toolkit/verify-understanding.svg)](https://agentmods.dev/skills/eai-org/agent-toolkit/verify-understanding)
Your own site
<a href="https://agentmods.dev/skills/eai-org/agent-toolkit/verify-understanding"><img src="https://agentmods.dev/badge/skills/eai-org/agent-toolkit/verify-understanding.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 499 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 $0.00044 $0.00499
Opus 5 $0.00022 $0.00249
Sonnet 5 $0.00009 $0.00100
Haiku 4.5 $0.00004 $0.00050

Measured 4d ago against content hash 2736c9657e89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-understanding 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 4d 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/verify-understanding/SKILL.md · 49 lines

What it actually says

Verify understanding

One goal, nothing more, nothing less: verify the engineer is ready to move to the implementation phase. Exercise their understanding of a feature before they work on it — the pipeline's other artifacts serve fresh agent sessions; this step serves the human. Active recall: the user produces the feature in their own words, you only steer and fix. Re-runnable: right after the ticket review, or days later just before implementation — every run starts fresh from the review file, no state kept between runs.

Input

A .TICKET-REVIEW.md. Read it and the ticket files and parent it links. A reference that exists only as a tracker URL (no local file) may be fetched read-only at conversation time.

The conversation

A conversation, not a test — the last sync between a dev and their PO before development starts.

  1. Ask the user to explain the feature in their own words: who uses it, what they see and do, why the feature exists, and what each ticket contributes.
  2. Let them produce the narrative. Probe one weak spot at a time; correct and complete only from the review file and the referenced materials — flag what those don't settle, never improvise requirements.
  3. Stay at that PO–dev depth: journey, actors, purpose, per-ticket contribution — not DTO, field, or architecture detail.

When the product's user-facing language differs from the conversation's, name each page, text, or element with its user-facing term in parentheses — "the client area (klantportaal)".

Done when the user has correctly produced — corrections absorbed — the journey, why the feature exists, and every input ticket's contribution: enough to start implementing. Close with a short wrap-up naming anything that stayed shaky, then point at /refine-ticket <ticket-file> per ticket, in the set's suggested execution order.

Boundaries

  • The conversation is the product: write no files.
  • Read-only on the tracker.
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. 4d ago First seen · 49 lines · 44 tokens per session scan A 2736c9657e89

Subscribe to this mod's changes

verify-understanding is a skill published in the GitHub repository eai-org/agent-toolkit (43 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 499 once invoked, about $0.0002 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

gsd-extract-learnings

Extract decisions, lessons, patterns, and surprises from completed phase artifacts.

open-gsd/gsd-core · 20 tokens

spec-kitty-orchestrator-api-operator

Teach agents and external systems how to use spec-kitty orchestrator-api to drive workflows from outside the host CLI. Triggers: "use orchestrator-api", "build a custom orchestrator", "automate externally", "integrate CI with spec-kitty", "call spec-kitty from another tool", "orchestrator contract", "external…

Priivacy-ai/spec-kitty · 125 tokens

direction-adjust

Capture a small-to-medium course correction the user realized mid-task (not from external review), record it as a numbered D-N entry in DECISIONS.md, update TASKSTATE.md to reflect the adjusted direction, and route back to the appropriate command. Use when you are mid-task (any phase past discovery) and realize the…

Mozurok/fhorja.dev · 201 tokens

prospec-learn

Feedback Promotion Pipeline - Collect session corrections, repeated verify FAILs and recurring review criticals into a version-controlled lessons ledger; score them with an explicit, reproducible rule (frequency + impact modules); and promote - only with explicit human approval - across three tiers (accumulating…

benwu95/prospec · 96 tokens

system-documentation

Establish, synchronise, audit, and review an opinionated repository documentation system across entrypoints, architecture, reference, explanation, tutorials, how-to guides, operations, audience indexes, and governance/lifecycle artefacts.

stefaniuk/loadout · 48 tokens

harvest-session-learnings

Scan the current working session and the active task's artifacts for reusable, generalizable lessons (what was tried, what failed and why, what surprised us, what the next task should do differently) and propose anchored entries to append to the task's LEARNINGS.md, the produce-side counterpart to the ADR-0017 consume…

Mozurok/fhorja.dev · 198 tokens