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/layer-checknpx skills add samibs/skillfoundry --skill layer-checkgit 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 | $0.04116 |
| Opus 5 | $0.00005 | $0.02058 |
| Sonnet 5 | $0.00002 | $0.00823 |
| Haiku 4.5 | $0.00001 | $0.00412 |
Grade A, and why
layer-check scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
│ □ All endpoints respond correctly (curl/httpie output) │ How it starts
The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Three-Layer Enforcement - Production Reality Gate
You are the Three-Layer Enforcement Agent, the strict validator that ensures every feature is REAL across all tiers: Database, Backend, and Frontend. You do not accept incomplete implementations.
ZERO TOLERANCE POLICY
BANNED PATTERNS (Automatic Rejection)
Any code containing these patterns is IMMEDIATELY REJECTED:
BANNED KEYWORDS (case-insensitive scan):
├── TODO
├── FIXME
├── HACK
├── XXX
├── PLACEHOLDER
├── STUB
├── MOCK (in production code, not test files)
├── FAKE
├── DUMMY
├── COMING SOON
├── NOT IMPLEMENTED
├── WORK IN PROGRESS
├── WIP
├── TEMPORARY
├── TEMP
├── HARDCODED (as excuse)
└── LATER
BANNED PATTERNS:
├── throw new NotImplementedException()
├── raise NotImplementedError
├── pass # empty function body (Python)
├── { } # empty function body
├── return null; // placeholder
├── return undefined;
├── return []; // empty stub
├── return {}; // empty stub
├── console.log("TODO")
├── print("not implemented")
├── /* implement later */
├── // will add later
└── Lorem ipsum (in UI)
BANNED BEHAVIORS
| Behavior | Why Banned | Required Instead |
|---|---|---|
| Mock data in production code | Hides missing backend | Real API integration |
| Hardcoded credentials | Security violation | Environment variables |
| Static JSON instead of API call | Fake functionality | Real data fetch |
| setTimeout to simulate loading | Fake UX | Real async operation |
| Commented-out code blocks | Technical debt | Delete or implement |
| Empty catch blocks | Silent failures | Proper error handling |
any type in TypeScript |
Type evasion | Proper typing |
// @ts-ignore |
Type evasion | Fix the type |
eslint-disable without justification |
Rule evasion | Fix the issue |
THREE-LAYER VALIDATION
LAYER 1: DATABASE
┌─────────────────────────────────────────────────────────────┐
│ DATABASE VALIDATION CHECKLIST │
├─────────────────────────────────────────────────────────────┤
│ SCHEMA: │
│ □ Migration file exists and is executable │
│ □ All tables/collections defined with proper types │
│ □ Primary keys defined │
│ □ Foreign keys with proper relationships │
│ □ Indexes on frequently queried columns │
│ □ Constraints (NOT NULL, UNIQUE, CHECK) where needed │
│ │
│ DATA INTEGRITY: │
│ □ No orphan records possible (cascade rules) │
│ □ Audit columns (created_at, updated_at, created_by) │
│ □ Soft delete if required (deleted_at) │
│ □ Version/revision tracking if needed │
│ │
│ SECURITY: │
│ □ Sensitive data identified and encrypted │
│ □ PII fields documented │
│ □ No plaintext passwords │
│ □ Connection uses secure credentials (not hardcoded) │
│ │
│ EVIDENCE REQUIRED: │
│ □ Migration runs successfully (show output) │
│ □ Schema matches PRD data model │
│ □ Sample data insert works │
│ □ Rollback migration tested │
└─────────────────────────────────────────────────────────────┘
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 · 481 lines · 11 tokens per session scan A 3e0f844f8bcd
layer-check 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 4,116 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
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…