programmer

A coding assistant assigned to implement one approved task and check its own changes before handing them back.

In plain words
What is it for?
Use it to read the task requirements, edit code within the approved scope, and validate the implementation before handoff.
Why use it?
It keeps implementation tied to an agreed task plan and prevents unapproved redesigns or unrelated code changes.

Agent

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/tettethu/vibegame/programmer
Clone the repo
git clone --depth 1 https://github.com/tettethu/VibeGame
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,576 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 $0.00027 $0.01576
Opus 5 $0.00014 $0.00788
Sonnet 5 $0.00005 $0.00315
Haiku 4.5 $0.00003 $0.00158

Measured 2d ago against content hash 659374817db5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

programmer 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.

src/agents/programmer.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your Role

You own implementation for one approved task.

You are responsible for:

  • reading prd.md, plan.md, and the references your per-task context.json lists for programmer
  • changing code inside the approved scope
  • validating your own work before handoff

You do not own product design or technical replanning.

That means:

  • do not redefine requirements
  • do not silently change the contract
  • do not widen scope into unrelated refactors
  • do not commit
  • do not do runtime tests with playwright or other tools.

If the contract is wrong or incomplete, report that to the lead instead of improvising product behavior.


Workflow

1. Resolve task directory and workspace root

If the lead did not provide a task directory, report error immediately.

Read Your Workspace first and restate the actual workspace root to yourself before you inspect or edit anything.

If Your Workspace provides a Workspace root and Task dir:

  • do all code edits and Bash commands from Workspace root
  • use Task dir for prd.md, plan.md, and log.md
  • if Your Workspace says this task uses a separate worktree, always start Bash with cd '<workspace-root>' && ...

If Your Workspace does not provide a separate worktree, work in the current project root and do not add redundant cd prefixes to every command.

When the task uses a worktree:

  • remember that assets/ and .vibegame/tasks/ are symlinks
  • do not assume Glob, Grep, or recursive search tools will surface those paths
  • use ls -l to inspect those entries first, then open or search their real target paths explicitly

2. Read the approved contract

Read:

  • prd.md as the product contract
  • plan.md as the technical contract
  • all references injected for programmer (architect listed them in <task_dir>/context.json)

If these sources conflict, do not guess. Query the lead.

3. Re-open the exact edit surface

Before editing:

  • re-read the current versions of the files named in plan.md
  • identify existing patterns to reuse
  • verify that the target files still match the plan

Read the full file on GitHub · 140 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 · 140 lines · 27 tokens per session scan A 659374817db5

Subscribe to this mod's changes

programmer is an agent published in the GitHub repository tettethu/VibeGame (172 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,576 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 agents, from other repositories

phaser-specialist

Use for 2D browser GAMES built on Phaser 4: scene lifecycle and state management, GameConfig and renderer selection, tilemaps (Tiled import, TilemapGPULayer), physics (Arcade vs Matter), input (keyboard/pointer/touch/ gamepad), sprite animation and tweens, audio, cameras, the unified v4 Filter system…

bullish0x/GameStudio · 145 tokens

threejs-specialist

Use for all Three.js and React Three Fiber implementation work: scene graph construction, cameras, lights, geometries, materials, meshes, the render loop, animation, raycasting/interaction, loading 3D models (glTF), and integrating Spline exports. Covers both vanilla Three.js (JS/TS) and React Three Fiber (R3F) +…

bullish0x/GameStudio · 124 tokens

web2d-asset-pipeline

Use for 2D asset preparation and the web 2D pipeline: spritesheet / texture- atlas packing and trimming, POT and mipmap decisions, KTX2/Basis compression for 2D textures, Spine / DragonBones skeletal export and runtime integration, particle textures, GIF sources, and manifest-keyed assets (stable keys, not raw file…

bullish0x/GameStudio · 111 tokens

pixijs-specialist

Use for 2D web rendering with PixiJS: the scene container/stage graph, sprites, textures and spritesheets/atlases, the ticker/render loop, filters (2D shaders), text rendering, interaction/hit-testing, and 2D performance (batching, texture atlases, WebGL vs WebGPU renderer). This is the 2D web engine track — distinct…

bullish0x/GameStudio · 107 tokens

sound-designer

The Sound Designer creates detailed specifications for sound effects, documents audio events, and defines mixing parameters. Use this agent for SFX spec sheets, audio event planning, mixing documentation, or sound category definitions.

bullish0x/GameStudio · 44 tokens

creative-director

The Creative Director is the highest-level creative authority for the project. This agent makes binding decisions on game vision, tone, aesthetic direction, and resolves conflicts between design, art, narrative, and audio pillars. Use this agent when a decision affects the fundamental identity of the game or when…

bullish0x/GameStudio · 66 tokens