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.
npx agentmods add commands/cbmono/ai-setup/verifygit clone --depth 1 https://github.com/cbmono/ai-setupWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00423 |
| Opus 5 | $0.00000 | $0.00211 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade A, and why
verify 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 yesterday.
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.
What it actually says
Pre-PR verification gate. Runs the project's checks and hands off to diagnosis on failure.
Usage
/verify— fast mode: typecheck / lint / test / build frompackage.jsonscripts (parallel when safe, no dep install)/verify --deep— deep mode: clean-install from the lockfile, then sequencedunit → integration → e2e, stopping on first red
Steps
- Dispatch the
build-validatoragent. Pass--deepthrough if the user included it. - If all green, say so and stop.
- If anything fails, dispatch the
oncall-guideagent with the failing output to classify the cause (regression / flake / environment / test data / configuration) and propose next steps. - End with
git status --short.
Do not modify files from this command. Fixes are applied by the user (or by a follow-up prompt), not by the verifier.
The build bucket stays in fast mode deliberately — it is the only check in the set that runs the
production bundler/compiler. tsc --noEmit emits nothing and the test runner uses its own transform
pipeline, so a build-only failure (an unmapped path alias, a file outside tsconfig's include,
build-time env validation, a route that only fails during static generation, a loader or plugin
error) is invisible to typecheck, lint and test alike. Moving it to --deep would put it behind a
clean install, i.e. behind CI in practice — and a gate that lets the build break is not a pre-PR
gate. It costs nothing where there is no build script: build-validator skips a bucket with no
matching script.
This command is the concrete tool that satisfies the superpowers:verification-before-completion discipline (no "done" claim without fresh evidence) for the pre-PR gate — report only what the check output actually shows, never "should pass".
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.
- yesterday First seen · 27 lines · 0 tokens per session scan A c9b051278ba0
verify is a command published in the GitHub repository cbmono/ai-setup (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 423 tokens. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.