agentrium: Skill for Claude Code

.claude/skills/verification-loop/SKILL.md

verification-loop is a skill for Claude Code from talayash/agentrium. It costs 14 tokens per session (526 once invoked), scanned A, original, MIT.

A pre-commit and pre-release checklist for checking a ClaudeTerminal application's Rust backend, TypeScript frontend, build, formatting, linting, and security-related requirements. Type checking finds code that uses values in invalid ways before the program runs.

In plain words
What is it for?
Use it before significant commits, releases, or after resolving merge conflicts to run the project's backend and frontend checks and validate their connection.
Why use it?
It gathers important project checks into one repeatable verification process, helping catch compilation, type, formatting, build, and integration problems early.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is talayash/agentrium's own configuration. It tells Claude Code how to work on agentrium itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentrium configures →

Reuse

Borrowing it

Nothing to install: this file belongs to talayash/agentrium. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/talayash/agentrium/master/.claude/skills/verification-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/talayash/agentrium

Made for: Claude Code.

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-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/talayash/agentrium/verification-loop/github.svg)](https://agentmods.dev/skills/talayash/agentrium/verification-loop)
Your own site
<a href="https://agentmods.dev/skills/talayash/agentrium/verification-loop"><img src="https://agentmods.dev/badge/skills/talayash/agentrium/verification-loop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verification-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/talayash/agentrium/verification-loop"><img src="https://agentmods.dev/badge/skills/talayash/agentrium/verification-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 526 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 41
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00014 $0.00526
Opus 5.5 $0.00006 $0.00210
Sonnet 5.5 $0.00003 $0.00105
Haiku 4.5 $0.00001 $0.00053

Measured 1mo ago against content hash abb60d2fb503, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verification-loop 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 1mo 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.

.claude/skills/verification-loop/SKILL.md · 79 lines

What it actually says

Verification Loop

A systematic verification pipeline that checks all aspects of project health before commits or releases.

When to Use

  • Before committing significant changes
  • Before creating a release
  • After resolving merge conflicts
  • When /verify command is invoked

Pipeline Phases

Phase 1: Rust Backend Compilation

cd src-tauri && cargo check 2>&1
  • Must compile with zero errors
  • Warnings are acceptable but should be noted

Phase 2: Rust Linting

cd src-tauri && cargo clippy -- -W clippy::all 2>&1
  • All clippy warnings should be addressed
  • #[allow(clippy::...)] only with justification

Phase 3: Rust Formatting

cd src-tauri && cargo fmt --check 2>&1
  • Must pass with no formatting changes needed

Phase 4: TypeScript Type Check

npx tsc --noEmit 2>&1
  • Zero type errors
  • Strict mode compliance

Phase 5: Frontend Build

npm run build 2>&1
  • Vite production build must succeed
  • Check for bundle size warnings

Phase 6: IPC Contract Validation

  • Every #[tauri::command] in commands.rs registered in main.rs
  • Every invoke() in frontend matches a registered command
  • Event names consistent between emit() and listen()

Phase 7: Security Quick Scan

  • No .unwrap() in production Rust code (use ? or .map_err())
  • No hardcoded secrets/tokens
  • No eval() or innerHTML in frontend
  • No console.log with sensitive data

Report Template

| Phase | Status | Duration | Notes |
|-------|--------|----------|-------|
| Rust compile | ✅/❌ | Xs | |
| Clippy | ✅/❌ | Xs | |
| Formatting | ✅/❌ | Xs | |
| TypeScript | ✅/❌ | Xs | |
| Vite build | ✅/❌ | Xs | |
| IPC contracts | ✅/❌ | - | |
| Security scan | ✅/❌ | - | |

**Result: PASS / FAIL**
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. 1mo ago Changed abb60d2fb503
  2. 1mo ago First seen · 79 lines · 14 tokens per session scan A 903e27e09be1

Subscribe to this mod's changes

verification-loop is a skill published in the GitHub repository talayash/agentrium (46 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 526 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

ratchet-files

Ratchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit ratchet that stops them from growing. Use when a commit is blocked because a file is over the size budget, when asked to find or split…

dzhng/skills · 0 tokens

github-review-pr

Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…

feiskyer/claude-code-settings · 90 tokens

recipe-front-review

Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.

shinpr/claude-code-workflows · 29 tokens

find-simplifications

Use when asked to find or plan Cherry Studio cleanup, simplification, refactoring, dead-code removal, duplicated state removal, unnecessary APIs, speculative generality, or library replacements, especially when the result should become evidence-backed proposed Agent Notes.

CherryHQ/cherry-studio · 53 tokens

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…

GCWing/BitFun · 116 tokens

pr-description-writer

Redacta una descripción de pull request clara y estructurada a partir de un diff de git, resumen de rama o lista de commits. Úsalo cuando te pidan escribir una descripción de PR, redactar una solicitud de cambios o documentar cambios de código. Produce una descripción con resumen, motivación, cambios realizados, pasos…

mohitagw15856/pm-claude-skills · 80 tokens