verify

verify is a skill for Claude Code, Codex from synaptiai/agent-capability-standard. It costs 37 tokens per session (2,165 once invoked), scanned A, original, Apache-2.0.

A verification tool that checks an artifact against tests, specifications, or fixed rules called invariants. It returns pass-or-fail evidence and records assumptions and actionable suggestions for failures.

In plain words
What is it for?
Validating code, configuration, files, API endpoints, hypotheses, system state, and changes against a test suite or written specification.
Why use it?
It replaces confidence based on inspection alone with checks tied to observable results and the expected behavior.

Skill for Claude CodeCodex

Part of the agent-capability-standard plugin — 42 skills, 2 hooks shipped together

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/synaptiai/agent-capability-standard/verify
Any agent
npx skills add synaptiai/agent-capability-standard --skill verify
Clone the repo
git clone --depth 1 https://github.com/synaptiai/agent-capability-standard

Made for: Claude Code, Codex.

Or install agent-capability-standard, the plugin that ships this one along with the rest of its 42 skills, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/verify.svg)](https://agentmods.dev/skills/synaptiai/agent-capability-standard/verify)
Your own site
<a href="https://agentmods.dev/skills/synaptiai/agent-capability-standard/verify"><img src="https://agentmods.dev/badge/skills/synaptiai/agent-capability-standard/verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,165 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 $0.00037 $0.02165
Opus 5 $0.00018 $0.01082
Sonnet 5 $0.00007 $0.00433
Haiku 4.5 $0.00004 $0.00216

Measured 4d ago against content hash ec944d4bc2af, 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify-state.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Live Context

Before verification, gather current state:

  • Working directory: !pwd
  • Git status: !git status --short 2>/dev/null || echo "Not a git repo"
  • Recent commits: !git log --oneline -5 2>/dev/null || echo "No git history"
  • Last modified files: !find . -type f -mmin -30 -not -path './.git/*' 2>/dev/null | head -10 || echo "None"

Intent

Execute verify to determine whether an artifact (code, configuration, state, output) conforms to a specification, passes tests, or satisfies declared invariants.

Success criteria:

  • Clear PASS or FAIL verdict with supporting evidence
  • Every check is grounded to observable output or file content
  • Failures include actionable fix suggestions
  • All assumptions about expected behavior are explicit

Compatible schemas:

  • schemas/output_schema.yaml

Inputs

Parameter Required Type Description
spec Yes string|object The specification, test suite, or invariants to check against
artifact Yes string|object The target being verified (file path, function, API endpoint, state)
constraints No object Verification constraints: timeout, test filter, coverage threshold
check_types No array Types of checks: assertion, invariant, regression, schema

Procedure

  1. Load specification: Read the spec/test/invariant definition

    • Identify testable assertions from the spec
    • Parse test commands or invariant expressions
    • Note any preconditions required for verification
  2. Examine artifact: Inspect the target being verified

    • Read relevant code, config, or state
    • Identify the specific behavior/properties to check
    • Check preconditions are met before running tests
  3. Execute checks: Run each verification check systematically

    • For test suites: execute via Bash, capture stdout/stderr
    • For invariants: evaluate conditions, record boolean results
    • For schema validation: compare structure against schema
    • Record timing and resource usage if relevant

Read the full file on GitHub · 280 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 280 lines · 37 tokens per session scan A ec944d4bc2af

Subscribe to this mod's changes

verify is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 37 tokens to every session and 2,165 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

gh

GitHub API access and project management automation for the hallucination-detector repo. Uses octokit with proxy-aware client for all GitHub operations — issues, PRs, labels, milestones, Projects V2. No gh CLI required.

bitflight-devops/hallucination-detector · 49 tokens

evaluate-options

Research and evaluate implementation options before presenting a recommendation. Use when multiple approaches exist for a problem and a decision is needed. Launches one background research agent per option in parallel, collects evidence-backed findings, then presents a recommendation grounded in observed data — not…

bitflight-devops/hallucination-detector · 97 tokens

delegate

Quick delegation template for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Task tool, or when preparing prompts for specialized agents. Provides the WHERE-WHAT-WHY framework. For comprehensive delegation guidance, activate the agent-orchestration how-to-delegate skill.

bitflight-devops/hallucination-detector · 60 tokens

beginner-tone

코딩도 AI도 처음인 초보자와 대화할 때 쓰는 말투·안전 지침. SoDamHarness 설치 시 자동 활성화.

sodam-ai/SoDam-Harness-Eng · 34 tokens

ai-safe-driver

Use when the agent keeps repeating a mistake, ignores a correction, retries a failed tool unchanged, breaks an output format again, drifts from the latest request, or makes excuses instead of diagnosing recurrence. Also use for a conversation health check, compaction decision, or new-session question.

ssauma/ai-safe-driver · 61 tokens

sodam-harness-self-check

작업을 끝내거나 "다 됐어요"라고 말하기 전에 실제로 작동하는지 점검하고 증거를 보여줄 때 사용. 위험·중요 작업 마무리, 완료 선언, 검증 요청 시 적용.

sodam-ai/SoDam-Harness-Eng · 51 tokens