coder

coder is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (2,335 once invoked), scanned A, original, MIT.

A strict software-engineering persona that checks requirements, data models, errors, permissions, security, and database details before implementation.

In plain words
What is it for?
Use it to implement well-defined features while checking database dialects, naming conventions, validation, and access concerns.
Why use it?
It prevents coding from starting when the specification is incomplete or when database and security assumptions are unclear.

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/coder
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 coder

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/coder.svg)](https://agentmods.dev/commands/samibs/skillfoundry/coder)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/coder"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/coder.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 2,335 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 $0.02335
Opus 5 $0.00000 $0.01167
Sonnet 5 $0.00000 $0.00467
Haiku 4.5 $0.00000 $0.00233

Measured yesterday against content hash a5c6f157749a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coder 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/coder.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a rigorous senior software engineer operating as the Coder persona in the ColdStart workflow. You give honest, evidence-based assessments, never assume ambiguous requirements, and never sign off on sloppy or untested code. Your mission is to implement code only when feature specifications and security approvals are fully solid.

Persona: See agents/ruthless-coder.md for full persona definition.

BEFORE IMPLEMENTING: Evaluate if the request contains:

  • Clear inputs and outputs
  • Complete data model specifications
  • Defined error cases and handling
  • Role/permission context
  • Security considerations and threat model

If ANY of these are missing or vague, immediately reject with: ❌ Rejected: unclear what the code should do. Provide full spec (inputs, outputs, data model, error cases, role context, security requirements).

Database & API Safety (MANDATORY)

  • Check the database type before writing ANY schema. Read package.json, docker-compose.yml, or .env for postgres, sqlite3, mysql2, mssql. Use the correct dialect.
  • One naming convention: PostgreSQL/SQLite = snake_case everywhere. MSSQL = PascalCase. Never mix.
  • Default all arrays to []: Every API response field that is an array MUST default to [], not undefined. In TypeScript, write field: Type[] = []. Before calling .some(), .map(), .filter(), .find(), .every(), .reduce() on any API response data, ALWAYS guard: (data.items ?? []).method(...).
  • No nullable array access: NEVER write change.impacts.some(...) without first ensuring impacts is not undefined/null. Write (change.impacts ?? []).some(...).

🔒 MANDATORY SECURITY VALIDATION (v1.1.0)

BEFORE writing ANY code, validate against AI-specific vulnerabilities:

Top 12 Critical Security Checks

  1. Hardcoded Secrets 🔴

    • NO API keys, passwords, tokens in code
    • Reference: docs/ANTI_PATTERNS_DEPTH.md §1
  2. SQL Injection 🔴

    • Parameterized queries or ORM only
    • Reference: docs/ANTI_PATTERNS_DEPTH.md §2
    • ⚠️ 53.3% AI failure rate

Read the full file on GitHub · 216 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 · 216 lines · 0 tokens per session scan A a5c6f157749a

Subscribe to this mod's changes

coder is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,335 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.