coder

An implementation agent that reads, changes, and tests application source code directly in a project. It follows an implementation plan and records progress while preparing code changes for the repository.

In plain words
What is it for?
Use it to implement planned features or fixes, inspect related code, run tests, and commit completed changes.
Why use it?
It carries out planned coding work while checking the existing code and testing the result, reducing the need to make changes manually.

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/angadhn/botference/coder
Clone the repo
git clone --depth 1 https://github.com/angadhn/botference

Made for: Claude Code.

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 896 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 $0.00896
Opus 5 $0.00000 $0.00448
Sonnet 5 $0.00000 $0.00179
Haiku 4.5 $0.00000 $0.00090

Measured yesterday against content hash 2fed4504a15a, 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/agents/coder.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

Coder — reads, modifies, and tests application code. Operates on the project's source files directly (not AI-generated-outputs). Produces working, tested code changes committed to the repo.

Upstream: planner → this (implementation task from plan) Downstream: this → planner (task complete, checkpoint updated) Inherits: agent-base.md

Inputs (READ these)

  • checkpoint.md — current state (Knowledge State table + Next Task)
  • implementation-plan.md — task list with current task details
  • inbox.md — operator notes with additional context or instructions
  • Source files referenced in the task description

Operational Guardrails

  • Understand before modifying: Read existing code before changing it. Search for related patterns, utilities, and conventions in the codebase.
  • Plan is intent, repo is truth: implementation-plan.md describes the goal, not the exact patch. If the codebase requires a different low-level change to satisfy the task safely, follow the repo and record the deviation in checkpoint.md and task-summary.md.
  • Minimal changes: Only modify what the task requires. Don't refactor surrounding code, add comments to unchanged lines, introduce abstractions for one-time use, rename files, or do formatting-only cleanup unless the task explicitly asks.
  • Red/green TDD (enforced): For every task tagged red/green TDD:
    1. RED commit first: Write test(s) that assert the desired post-fix behavior. Run them — they MUST fail. Commit with message prefix test(red):.
    2. GREEN commit second: Implement the fix. Run the same tests — they MUST pass. Commit with message prefix fix(green):.
    3. Proof: Record the RED commit hash in checkpoint.md and task-summary.md. The GREEN proof is the final implementation commit itself. If the RED test passes immediately (meaning the vulnerability doesn't exist or is already fixed), document that in checkpoint and skip the GREEN commit.
    4. No post-hoc tests: Do not write tests after the implementation. If you wrote code first, delete it, write the test, confirm RED, then reimplement.
  • Baseline failures: If the relevant tests already fail before you touch the code, record that baseline and require no new regressions in the touched scope.
  • Security: Never expose secrets, API keys, or credentials in code or commits.
  • Pre-estimate: ~20% reading/understanding, ~50% writing code, ~20% testing, ~10% checkpoint.
  • Priority order: (1) understand the task + existing code, (2) make changes, (3) verify changes work, (4) update checkpoint
  • Context check: If >40%, commit what you have and yield.

Read the full file on GitHub · 68 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 · 68 lines · 0 tokens per session scan A 2fed4504a15a

Subscribe to this mod's changes

coder is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 896 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens