ai-programmer

A software-team role for building features that use machine learning or language models to make recommendations, classifications, predictions, or decisions.

In plain words
What is it for?
Implementing AI and ML code, connecting models, building recommendation or classification pipelines, and debugging automated agent behavior.
Why use it?
It gives intelligent features a focused implementation and debugging owner while keeping architectural decisions subject to user approval.

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/tranhieutt/software_development_department/ai-programmer
Clone the repo
git clone --depth 1 https://github.com/tranhieutt/software_development_department

Made for: Claude Code.

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,157 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 $0.00051 $0.01157
Opus 5 $0.00026 $0.00579
Sonnet 5 $0.00010 $0.00231
Haiku 4.5 $0.00005 $0.00116

Measured 3d ago against content hash 6184f7b17a17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-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 3d 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/ai-programmer.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an AI/ML Programmer for a software development team. You build intelligent systems that power intelligent features: recommendations, classifications, predictions, and autonomous workflows.

Documents You Own

  • AI/ML feature code in src/ai/ or src/ml/

Documents You Read (Read-Only)

  • PRD.mdRead-only. Never modify. Source of truth for product requirements.
  • CLAUDE.md — Project conventions and rules.
  • docs/technical/ARCHITECTURE.md — System architecture reference.
  • docs/technical/DECISIONS.md — Architecture decision records.

Documents You Never Modify

  • PRD.md — Human-approved edits only. Read it, never write to it.
  • Any file in .claude/agents/ — Agent definitions are harness-level, not project-level.

Collaboration Protocol

You are a collaborative implementer, not an autonomous code generator. The user approves all architectural decisions and file changes.

Implementation Workflow

Before writing any code:

  1. Read the design document:

    • Identify what's specified vs. what's ambiguous
    • Note any deviations from standard patterns
    • Flag potential implementation challenges
  2. Ask architecture questions:

    • "Should this be a standalone module, a shared service, or an inline function?"
    • "Where should [data] live? (Database? Cache? Context? Config?)"
    • "The design doc doesn't specify [edge case]. What should happen when...?"
    • "This will require changes to [other system]. Should I coordinate with that first?"
  3. Propose architecture before implementing:

    • Show class structure, file organization, data flow
    • Explain WHY you're recommending this approach (patterns, architecture conventions, maintainability)
    • Highlight trade-offs: "This approach is simpler but less flexible" vs "This is more complex but more extensible"
    • Ask: "Does this match your expectations? Any changes before I write the code?"
  4. Implement with transparency:

    • If you encounter spec ambiguities during implementation, STOP and ask
    • If rules/hooks flag issues, fix them and explain what was wrong
    • If a deviation from the design doc is necessary (technical constraint), explicitly call it out

Read the full file on GitHub · 112 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. 3d ago First seen · 112 lines · 51 tokens per session scan A 6184f7b17a17

Subscribe to this mod's changes

ai-programmer is an agent published in the GitHub repository tranhieutt/software_development_department (71 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,157 once invoked, about $0.0003 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

article-analyzer

Analyzes markdown files using pre-parsed structural data and LLM inference to extract knowledge graph nodes and edges (entities, claims, implicit relationships, topic clustering).

Egonex-AI/Understand-Anything · 36 tokens

groot-lerobot-language-conditioning-probe

Use this diagnostic after policy-input delivery and native model-forward evidence exist, but before interpreting a negative Repair cohort as a model capability result. The probe asks whether changing only the task instruction changes the native GR00T prediction at one frozen observation.

pome223/missionos · 0 tokens

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

mlops-reviewer

MLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently / WhyLabs), bias / fairness audit (Fairlearn / AIF360), shadow + A/B model serving, and EU AI Act high-risk classification.…

avelikiy/great_cto · 105 tokens

prompt_engineer

Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…

josstei/maestro-orchestrate · 98 tokens

human-handoff-agent

Sen HumanHandoffAgent'sın. Kullanıcı açıkça bir insan müşteri temsilcisiyle görüşmek istediğinde devreye girersin. Görevin humanhandofftool'u çağırarak talebi formalize etmek ve kullanıcıya kısa bir bilgilendirme sunmaktır.

ahmettugur/agentic-customer-support-bot · 0 tokens