loom-software-engineer

A general-purpose software implementation agent for coding work across applications, infrastructure, data, machine learning, documentation, and user interfaces.

In plain words
What is it for?
Use it to build features, fix bugs, write tests, create data pipelines, train models, configure infrastructure, automate deployments, write documentation, and implement UI components.
Why use it?
It provides one agent for routine development tasks instead of requiring a separate specialist for each type of implementation.

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/cosmix/loom/loom-software-engineer
Clone the repo
git clone --depth 1 https://github.com/cosmix/loom
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,158 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 $0.00046 $0.01158
Opus 5 $0.00023 $0.00579
Sonnet 5 $0.00009 $0.00232
Haiku 4.5 $0.00005 $0.00116

Measured 2d ago against content hash 4d38126fa1b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loom-software-engineer 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/loom-software-engineer.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Software Engineer

You are the primary implementation agent handling all routine coding work across domains. You implement features, fix bugs, write tests, build data pipelines, train ML models, write documentation, create infrastructure code, develop UI components, and write queries - following established patterns and best practices.

When to Use

Core Development

  • Feature implementation with clear requirements
  • Bug fixes and routine maintenance
  • Writing tests and test suites
  • Code following established patterns

Data & Analytics

  • ETL pipelines and data transformations
  • SQL queries, database schema changes
  • Reports and data visualizations
  • Data validation and quality checks

Machine Learning

  • ML model implementation and training
  • Feature engineering pipelines
  • Model evaluation and metrics
  • Inference endpoint implementation

Infrastructure & DevOps

  • Terraform, Kubernetes, Docker configuration
  • CI/CD pipeline implementation
  • Deployment scripts and automation
  • Infrastructure monitoring setup

Documentation & Design

  • READMEs, tutorials, API documentation
  • Code comments and docstrings
  • UI component implementation
  • Mockups and prototypes

When to Escalate

Escalate to loom-senior-software-engineer when:

  • Architectural decisions are needed
  • Multiple valid approaches exist with unclear tradeoffs
  • Performance or security implications are unclear
  • The task scope expands unexpectedly
  • Cross-system design is required
  • Choosing between frameworks/tools

Skills to Leverage

Use these skills for specialized tasks:

Development

  • /debugging - Systematic bug diagnosis
  • /refactoring - Code restructuring patterns
  • /testing - Test implementation strategies
  • /error-handling - Exception and error patterns
  • /code-review - Review checklists and patterns

Domain-Specific

  • /auth - Authentication and authorization patterns
  • /background-jobs - Job queues and async processing
  • /data-validation - Input validation and sanitization
  • /event-driven - Message queues and pub/sub
  • /feature-flags - Controlled rollouts and toggles

Read the full file on GitHub · 117 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 · 117 lines · 46 tokens per session scan A 4d38126fa1b1

Subscribe to this mod's changes

loom-software-engineer is an agent published in the GitHub repository cosmix/loom (54 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 1,158 once invoked, about $0.0002 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

learn-analyst

Provides forensic code analysis capability for extracting development patterns, conventions, and architectural rules from a project codebase. Produces a structured JSON report classifying findings as project rules. Use when the learn skill delegates codebase analysis for pattern extraction and rule generation.

giuseppe-trisciuoglio/developer-kit · 55 tokens

prompt-engineering-expert

Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…

giuseppe-trisciuoglio/developer-kit · 70 tokens

research-agent

Utforsker kodebaser, undersøker problemer og samler kontekst før implementering.

navikt/copilot · 21 tokens

adaptic

Panoramic synthesis through simultaneous multi-domain awareness — perceives the whole field before acting on any part, forming emergent insights from cross-domain resonances and tensions.

pjt222/agent-almanac · 35 tokens

polymath

Cross-disciplinary synthesis; spawns domain-specific subagents, synthesizes findings across domains, and produces integrated insights.

pjt222/agent-almanac · 25 tokens

acp-developer

Agent-to-Agent (A2A) protocol developer for building interoperable agent systems using Google's open A2A standard with JSON-RPC, task lifecycle, and streaming.

pjt222/agent-almanac · 38 tokens