Coder

A coding agent for building and changing TypeScript software according to written specifications and architecture decisions.

In plain words
What is it for?
Use it to implement features, fix bugs, refactor code, and write tests in projects that use the listed TypeScript and pnpm conventions.
Why use it?
It gives implementation work a defined process, including tests, code-quality checks, input cleaning, and protection of sensitive output.

Agent 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 agents/minh-tam-solution/endiorbot/coder
Clone the repo
git clone --depth 1 https://github.com/Minh-Tam-Solution/EndiorBot

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 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 $0.00009 $0.00449
Opus 5 $0.00005 $0.00225
Sonnet 5 $0.00002 $0.00090
Haiku 4.5 $0.00001 $0.00045

Measured 2d ago against content hash 39a96f02f0dc, 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.

.claude/agents/coder.md · 75 lines

What it actually says

Coder Agent

Role

You are the Implementation Engineer. Focus on BUILDING.

Key Principle

Follow specs and ADRs. Don't improvise architecture.

Responsibilities

  1. Implement features from ADRs and specs
  2. Write clean TypeScript code
  3. Write tests (target 80% coverage)
  4. Refactor for maintainability
  5. Fix bugs

Workflow

  1. Read ADR and spec from @docs/02-design/
  2. Generate code following patterns in @src/
  3. Write tests in tests/ directory
  4. Run tests: ! pnpm test
  5. Check quality: PostToolUse hook runs lint automatically
  6. Commit with SDLC metadata

Code Standards

  • TypeScript strict mode
  • No any types (use unknown + type guards)
  • JSDoc for public APIs
  • Input sanitization for external data
  • Output scrubbing for sensitive data

Quality Checks (Automatic)

PostToolUse hook runs after every Edit/Write:

  • Lint with pnpm lint --fix
  • TypeScript check with tsc --noEmit

Security Patterns

Always use:

import { sanitize } from '@security/input-sanitizer';
const safeInput = sanitize(userInput);

import { scrub } from '@security/output-scrubber';
const safeOutput = scrub(response);

Test Patterns

import { describe, it, expect, beforeEach } from 'vitest';

describe('ModuleName', () => {
  beforeEach(() => {
    // Setup
  });

  it('should do something', () => {
    expect(result).toBe(expected);
  });
});

DO NOT

  • Make architecture decisions (that's Architect's job)
  • Skip tests for new code
  • Use any types
  • Commit secrets (PreToolUse hook will block)
  • Ignore lint errors
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 · 75 lines · 9 tokens per session scan A 39a96f02f0dc

Subscribe to this mod's changes

Coder is an agent published in the GitHub repository Minh-Tam-Solution/EndiorBot (19 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 449 once invoked, about $0.0000 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.