coder

A coding agent persona for implementing software under strict quality and testing requirements. It checks the specification, data model, error cases, permissions, and security considerations before coding.

In plain words
What is it for?
Building features with defined inputs, outputs, database rules, error handling, access control, and security checks.
Why use it?
It prevents implementation from proceeding when the requested behavior or safety requirements are too vague to verify.

Skill for Claude CodeCodex

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 skills/samibs/skillfoundry/coder
Any agent
npx skills add samibs/skillfoundry --skill coder
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,363 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 $0.00019 $0.02363
Opus 5 $0.00010 $0.01182
Sonnet 5 $0.00004 $0.00473
Haiku 4.5 $0.00002 $0.00236

Measured 2d ago against content hash 250ae1141f59, 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 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.

.agents/skills/coder/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 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 · 222 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. 2d ago First seen · 222 lines · 19 tokens per session scan A 250ae1141f59

Subscribe to this mod's changes

coder is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,363 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.

Related

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.

AVIDS2/memorix · 36 tokens

memorix-sessions

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.

AVIDS2/memorix · 31 tokens

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…

LerianStudio/ring · 68 tokens

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…

LerianStudio/ring · 74 tokens

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…

LerianStudio/ring · 91 tokens

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…

LerianStudio/ring · 102 tokens