agentsclimarketplace

Loop verify

Skill cbdreamer11/CB-loop-kit-claude-plugin/skills/loop-verify

A session-based working method for coding agents: plan in thin complete slices, build one at a time, verify by observing real behaviour, hand off cleanly. Skills + agents + 2 hooks for Claude Code.

Install
npx -y skills add cbdreamer11/CB-loop-kit-claude-plugin --skill loop-verify

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 13 days oldThe repository was created 13 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Runs this project's verification contract and decides honestly whether something is verified, a gap, or a lie. Use before calling anything done, and whenever a report says "should work".

SKILL.md

2.6 KB, 595 tokens by cl100k_base, as published. Nobody here has run it

Verify for real

Read .loop/VERIFY.md and run the slots that apply to what changed. Then write down what you observed, in the words of what you saw — not in the words of what you hoped.

The three things that are not verification

  1. A green build. It proves the code compiles. Nothing else.
  2. "I read the code and it looks right." The bug you are looking for is exactly the one that looks right.
  3. "It should work." Then it is not verified. Say that instead.

Add two more that fool people constantly:

  1. An exit code of 0 — a command can succeed while doing nothing.
  2. An HTTP 200 — many servers answer 200 for a page that does not exist. Verify by finding a string that only exists in the new behaviour, not by status code.

What counts

Each slot must produce an artifact or a direct observation:

  • BUILD — the project's build/test command, green. Necessary, never sufficient.
  • OBSERVE — the thing itself, doing its thing: a page rendered in a real browser with a clean console and a real interaction (click, type, navigate); a CLI run with its real output; an endpoint returning the new field. A screenshot or captured output is the artifact.
  • DATA — query the store and confirm the effect: the row exists, the value changed, the wrong value is refused.
  • MONEY — if money moves, use the provider's test mode and confirm the resulting state changed for real. Never test with live money.

Testing against a real system

If the project has a test database or a seeded environment, use it: set up, run, tear down. That is the default. Working against a live system is an exception that must be declared in .loop/VERIFY.md, and when it is unavoidable: wrap in a transaction and roll back, or restore the fixtures afterwards and confirm nothing was left behind.

Two traps worth naming: your own tooling may run with more privileges than a real user, which hides permission bugs — check with the actual role. And a check that passes for you may fail for a signed-out visitor — check both.

The verdict

For each slot: VERIFIED (with the one line of what you observed), GAP (with the reason it cannot be checked here — a missing access, no browser, no test environment), or FAILED (go back to building). A slot may not be silently skipped. If a required slot is a GAP, the item is not done — it is delivered with a declared gap, and it says so in .loop/STATE.md.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.