verification-controller

verification-controller is a skill for Claude Code from ihabkhaled/AI-Psychiatry. It costs 29 tokens per session (205 once invoked), scanned A, original, MIT.

A procedure for deciding what evidence is needed to confirm that work is correct and whether existing checks are still valid.

In plain words
What is it for?
It helps map requirements to checks, record their results and scope, determine whether later changes invalidate them, and identify any missing proof.
Why use it?
It prevents unnecessary repeat testing while ensuring that every required condition has current proof.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-psychiatry plugin — 55 skills shipped together

Good fit It helps map requirements to checks, record their results and scope, determine whether later changes invalidate them, and identify any missing proof.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ihabkhaled/ai-psychiatry/verification-controller
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.

Any agent
npx skills add ihabkhaled/AI-Psychiatry --skill verification-controller
Clone the repo
git clone --depth 1 https://github.com/ihabkhaled/AI-Psychiatry

Made for: Claude Code.

Or install ai-psychiatry, the plugin that ships this one along with the rest of its 55 skills.

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 verification-controller

README.md
[![agentmods](https://agentmods.dev/badge/skills/ihabkhaled/ai-psychiatry/verification-controller.svg)](https://agentmods.dev/skills/ihabkhaled/ai-psychiatry/verification-controller)
Your own site
<a href="https://agentmods.dev/skills/ihabkhaled/ai-psychiatry/verification-controller"><img src="https://agentmods.dev/badge/skills/ihabkhaled/ai-psychiatry/verification-controller.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 205 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00029 $0.00205
Opus 5 $0.00015 $0.00102
Sonnet 5 $0.00006 $0.00041
Haiku 4.5 $0.00003 $0.00020

Measured 7d ago against content hash 6954dc4dd65b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

verification-controller 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 7d 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.

.ai/skills/verification-controller/SKILL.md · 37 lines

What it actually says

Verification Controller

Core principle

Verification is complete when each required condition has sufficient current proof; compulsive rechecking is prohibited.

Procedure

  1. List acceptance conditions requiring proof.
  2. Choose the smallest sufficient command or observation for each.
  3. Record result, scope, and timestamp or source state.
  4. Check whether later changes invalidated the proof.
  5. Reject equivalent reruns without relevant change or incomplete proof.
  6. Mark verification sufficient and continue or complete.

Required output

Condition-to-proof mapping, validity decision, and next unmet proof.

Limits

At most 2 equivalent passes without relevant change.

Common mistakes

Do not seek subjective certainty, recursively inspect unrelated paths, or repeat a check with different syntax.

Stop condition

Stop verification when all required proof is current or a specific missing proof is named.

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. 7d ago First seen · 37 lines · 29 tokens per session scan A 6954dc4dd65b

Subscribe to this mod's changes

verification-controller is a skill published in the GitHub repository ihabkhaled/AI-Psychiatry (3 stars, last pushed 23d ago), licensed MIT. It adds 29 tokens to every session and 205 once invoked, about $0.0001 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

implement

Use when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify. Enforces TDD: a failing test comes before the code that makes it pass, one task at a time, appended to a progress ledger that survives compaction. Delegates test tooling…

ericrisco/rsc-harness · 123 tokens

python

Use when the task is Python itself, in any framework or none: PEP 695 generics, mypy --strict typing, dataclass/Protocol/TypedDict/Enum choices, asyncio.TaskGroup, stdlib idioms, src/ layout + pyproject.toml with uv, ruff+mypy+pytest gate. NOT a FastAPI/ASGI service (that is fastapi), NOT a deep pytest suite (that is…

ericrisco/rsc-harness · 94 tokens

agent-eval

Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…

ericrisco/rsc-harness · 79 tokens

csharp-dotnet

Use when writing, reviewing, testing, or shipping C# / .NET code — ASP.NET Core APIs (minimal APIs vs controllers), EF Core data access, async correctness, solution layout in .cs/.csproj/.sln. NOT a Java/Spring backend (that is spring-boot), NOT a Node/TypeScript backend (that is nestjs), NOT framework-neutral REST…

ericrisco/rsc-harness · 89 tokens

debug

Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be reproduced and proven before any fix. On-demand; callable mid-implement. NOT a feature to spec or build (that is specify/implement), NOT the lint/test gate (that is verify), NOT adversarial diff…

ericrisco/rsc-harness · 85 tokens

e2e-testing

Use when writing or stabilizing Playwright tests that drive a real browser through multi-step journeys — durable locators, web-first assertions, storageState auth, trace/retries, and flakes that only bite in CI. NOT in-process component tests (that is testing-web), NOT WCAG auditing (that is accessibility), NOT the…

ericrisco/rsc-harness · 79 tokens