verify

A command template for running an application or its tests and checking the observed result. It is designed to be filled in with the real commands used by the project’s programming language and tools.

In plain words
What is it for?
Use it after code changes to choose and run the project’s test, development, or verification command, then inspect the result rather than relying only on the exit code.
Why use it?
A successful build only shows that code can compile; it does not show that the feature works. This requires a change to be exercised and its behavior checked.

Command

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 commands/peterkrueck/claude-code-development-kit/verify
Clone the repo
git clone --depth 1 https://github.com/peterkrueck/Claude-Code-Development-Kit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 716 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00000 $0.00716
Opus 5 $0.00000 $0.00358
Sonnet 5 $0.00000 $0.00143
Haiku 4.5 $0.00000 $0.00072

Measured 2d ago against content hash 6fcba9f676c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

verify scanned grade C with 2 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Database: dry-run the migration on a throwaway/copy, then assert post-state with queries. e.g. apply the migration to a scratch DB, run SELECTs that confirm the schema/data is what you expect, and check rollback wor

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

or `curl -fsS <url>` piped into an assertion for an endpoint.
commands/verify.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Command

Run the app or its tests to confirm a change actually works — observed behavior, not just "it compiles." Compiling proves the types line up; it does not prove the feature does what you intended. This command makes you exercise the change and watch the result.

Usage: /verify [what to check]

Pairs with /review-work, which reads the diff for bugs before you run anything — /verify is the run-it-and-watch step that confirms the change behaves.


This is a TEMPLATE

The kit is cross-stack, so this command ships with no live commands — every stack section below is a commented placeholder. Fill in the one(s) your project uses and delete the rest. Discover the real command from the repo (test runner in package.json / Makefile / pyproject.toml / Cargo.toml / a CI workflow, or your docs/ai-context/*.md) rather than hardcoding a guess. If you can't find one, ask the user instead of assuming.

Process

  1. Identify what changedgit diff --stat HEAD — and what behavior it should produce.
  2. Pick the verification path for the stack(s) the diff touches (sections below).
  3. Run it and OBSERVE. A green exit code is necessary, not sufficient — confirm the behavior (right output, right state, right pixels). A test that runs but asserts nothing meaningful has verified nothing.
  4. On failure, fix and re-run until the observed behavior matches intent. Surface non-trivial fixes to the user.
  5. Report what you ran, what you observed, and whether it matched intent.

Customize per stack

Uncomment and complete the section(s) that apply to your project. These are EXAMPLES — replace with your repo's real commands.

Read the full file on GitHub · 53 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 · 53 lines · 0 tokens per session scan C 6fcba9f676c1

Subscribe to this mod's changes

verify is a command published in the GitHub repository peterkrueck/Claude-Code-Development-Kit (1,380 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 716 tokens. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.