verify

A verification command for checking whether a software change works in practice. It distinguishes tests, which check written assertions, from directly running the feature and observing its real output.

In plain words
What is it for?
Use it after a change to define concrete expected behavior, start the project, exercise the affected page, API, command, or workflow, and record what actually happened.
Why use it?
It catches problems that automated tests may miss, such as a page failing to render, an endpoint returning an error, or a command producing the wrong result.

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/jpesewang/solo-dev-workflow/verify
Clone the repo
git clone --depth 1 https://github.com/jpeseWang/solo-dev-workflow
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 973 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00973
Opus 5 $0.00000 $0.00487
Sonnet 5 $0.00000 $0.00195
Haiku 4.5 $0.00000 $0.00097

Measured 2d ago against content hash af2b19650c51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify scanned grade A with 1 finding 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.

Makes network callslowCapability

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

curl -sf http://localhost:3000 >/dev/null && break
variants/solo/commands/verify.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify

Run the thing and look at it. Tests passing is not the same as the feature working.

/test proves the assertions you wrote are satisfied. This proves the software does what the task asked. They fail differently: a test suite can be entirely green while the button doesn't render, the endpoint 500s on the real payload, or the CLI prints the wrong thing.

The output of this command is what you observed, never what you expect to happen. If you did not run it, say you did not run it.

Input: optional — what to check (the settings page, POST /api/export). Empty means: work out what the current change affects and verify that.


Step 1 — Work out what "working" looks like

One or two concrete, checkable statements. Not "the export feature works" but:

  • GET /api/export?format=csv returns 200 with a text/csv body and a header row
  • the Settings page renders the new toggle, and clicking it persists after reload

If the task came from TASKS.md or an issue, its acceptance points are these.

Step 2 — Start it

Use the project's own run command from Project context in AGENTS.md:

<run/dev command>          # e.g. pnpm dev, go run ./cmd/server, make up

Run it in the background and capture output — you'll need the logs when it misbehaves. Wait for the ready signal rather than a fixed sleep, and give up with a clear message if it never comes:

for i in $(seq 1 60); do
  curl -sf http://localhost:3000 >/dev/null && break
  sleep 1
done

If it won't start, stop here and report that. A server that doesn't boot is the finding — don't work around it to reach the part you meant to test.

Step 3 — Exercise it

Pick the cheapest tool that actually observes the result:

Kind of change How to verify
HTTP API curl the real route with a real payload; check status, headers, body shape
CLI Run it with real arguments; check exit code and stdout
Web UI Open the route in a browser you can script, screenshot it, read the console
Background job Trigger it; check the side effect (row written, file produced, message sent)
Library A scratch script that imports it and calls it the way a consumer would

Read the full file on GitHub · 99 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 · 99 lines · 0 tokens per session scan A af2b19650c51

Subscribe to this mod's changes

verify is a command published in the GitHub repository jpeseWang/solo-dev-workflow (2 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 973 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.