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.
npx agentmods add skills/samibs/skillfoundry/anvilnpx skills add samibs/skillfoundry --skill anvilgit clone --depth 1 https://github.com/samibs/skillfoundryWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00011 | $0.03170 |
| Opus 5 | $0.00005 | $0.01585 |
| Sonnet 5 | $0.00002 | $0.00634 |
| Haiku 4.5 | $0.00001 | $0.00317 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 355 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 theaprefix (/anvil a3), nevert3. 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 |
What ships with it
1 file 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.
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.
- 2d ago First seen · 355 lines · 11 tokens per session scan A ac20626d1885
anvil is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 3,170 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 2026-08-30.
Other skills, from other repositories
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…