anvil

anvil is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (3,148 once invoked), scanned A, original, MIT.

A multi-stage quality gate that checks changed code and stories through syntax checks, smoke tests, adversarial review, security scanning, contract checks, and risk assessment.

In plain words
What is it for?
Use it to run all checks or a selected validation tier on the current story, changed files, or a specific file.
Why use it?
It catches problems between development stages, such as unsafe code, mismatched API behavior, or changes outside the intended scope.

Command for Claude Code

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 commands/samibs/skillfoundry/anvil
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

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 anvil

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/anvil.svg)](https://agentmods.dev/commands/samibs/skillfoundry/anvil)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/anvil"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/anvil.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,148 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 $0.00000 $0.03148
Opus 5 $0.00000 $0.01574
Sonnet 5 $0.00000 $0.00630
Haiku 4.5 $0.00000 $0.00315

Measured yesterday against content hash 62b9084cb5e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anvil 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.

.claude/commands/anvil.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/anvil - The Anvil Quality Gate

6-tier (A1–A6) agent-handoff validation system that catches issues between every agent phase.

Namespace: Anvil tiers are A1–A6 — distinct from the CLI quality gates T0–T7 (sf_cli/core/gates.ts). Different checks AND a different count (6 Anvil tiers vs 8 CLI gates); e.g. Anvil A3 = Self-Adversarial Review, CLI gate T3 = Tests. To avoid confusion, invoke Anvil tiers with the a prefix (/anvil a3), never t3. Canonical definition: agents/_anvil-protocol.md.


Usage

/anvil                    Run all tiers on current story/changed files
/anvil a1                 Tier A1 only (shell checks: syntax, patterns, imports, SAST)
/anvil a1 <file>          Tier A1 on specific file
/anvil a2                 Tier A2 (canary smoke test)
/anvil a3                 Tier A3 (self-adversarial review of last implementation)
/anvil a4                 Tier A4 (scope validation + Semgrep SAST deep scan)
/anvil a4 --sast-only     Tier A4 SAST scan only (skip scope diff)
/anvil a5                 Tier A5 (contract enforcement: API spec vs implementation)
/anvil a6                 Tier A6 (shadow tester: risk assessment of changed code)
/anvil --report           Full Anvil report on last story

Instructions

You are The Anvil — the quality gate that strikes between every agent handoff. When /anvil is invoked, run validation checks on the current story or changed files.

The 6 Tiers

Tier Name Type What It Catches
A1 Shell Pre-Flight Shell script (no LLM) Syntax errors, banned patterns, missing files, Semgrep SAST (if installed)
A2 Canary Smoke Test Quick execution test Module won't import, won't compile
A3 Self-Adversarial Review Coder self-critique Untested failure modes, blind spots
A4 Scope + SAST Diff comparison + Semgrep deep scan Scope creep, incomplete implementation, OWASP Top 10, hardcoded secrets
A5 Contract Enforcement API contract check API drift, wrong signatures
A6 Shadow Tester Risk assessment Priority risks for Tester

Read the full file on GitHub · 349 lines

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. yesterday First seen · 349 lines · 0 tokens per session scan A 62b9084cb5e8

Subscribe to this mod's changes

anvil is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,148 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 2026-09-03.