verify

A verification skill that checks whether work is ready to ship using the project’s configured checks. It reports evidence from those checks instead of treating completion as an opinion.

In plain words
What is it for?
Running verification before a commit or pull request, checking whether work is done, and reporting the actual pass or fail output.
Why use it?
It reduces the risk of committing or opening a pull request when tests or other required checks still fail.

Skill for Claude CodeCodex

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/promptpartner/agentsmith/verify
Any agent
npx skills add PromptPartner/agentsmith --skill verify
Clone the repo
git clone --depth 1 https://github.com/PromptPartner/agentsmith

Made for: Claude Code, Codex.

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 540 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 $0.00069 $0.00540
Opus 5 $0.00034 $0.00270
Sonnet 5 $0.00014 $0.00108
Haiku 4.5 $0.00007 $0.00054

Measured 2d ago against content hash e5431963c657, 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 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 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.

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/SKILL.md · 40 lines

What it actually says

Verify — evidence before "done"

"Verified" is not a feeling; it's output you can point at. Never claim passing without showing it (R5 + verification-before-completion).

When this fires

"verify" / "is this done / shippable / ready to merge?" / just before a commit or PR.

Runtime neutrality

The verification runner and evidence standard are client-neutral. Never infer the active agent from this skill's install path: .agents/skills is the shared Agent Skills location. Use canonical AGENTS.md when an instruction is relevant.

Fast path — if the Agentsmith CLI is available

  1. Run agentsmith verify (or the installed-project shim .agentsmith/agentsmith verify on macOS/Linux and .agentsmith\\agentsmith.cmd verify on Windows). It runs every phase in .harness/verify.conf and stops at the first failure). --list shows the phases; --only <tag> iterates just one.
  2. On a failure: read the label + command it printed, explain in plain language what broke, and point at that phase's line in .harness/verify.conf to fix or refine.
  3. Report the actual pass/fail output — not a summary of intent.

Fallback — no runner or no conf

  1. Say so plainly, and look at .harness/verify.conf.example for the intended phases.
  2. Run the obvious checks for this project directly and show their output: build, test, lint, link/render check, a dry-run. For non-code work, "verify" = open the artifact and confirm it renders / the numbers reconcile / the links resolve.
  3. If nothing is wired yet, propose the phases this project needs and offer to write .harness/verify.conf — but still run the checks by hand this time.

Report

State each check and its evidence: "build ok, 42 tests green, lint clean" — with the output, not "should pass". Anything skipped is "deferred: reason", never silence.

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 · 40 lines · 69 tokens per session scan A e5431963c657

Subscribe to this mod's changes

verify is a skill published in the GitHub repository PromptPartner/agentsmith (188 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 540 once invoked, about $0.0003 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.