forja-dev

A software developer and architect agent for planning, building, testing, and documenting applications. It follows a team process with separate planning and quality-check roles.

In plain words
What is it for?
Use it for implementation, architecture choices, refactoring, infrastructure, continuous integration and delivery, and technical documentation. It also covers writing tests and checking the finished work.
Why use it?
It gives coding work a repeatable structure, including design decisions, tests, security checks, and a handoff for review.

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/davepoon/buildwithclaude/forja-dev
Clone the repo
git clone --depth 1 https://github.com/davepoon/buildwithclaude
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 366 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 $0.00047 $0.00366
Opus 5 $0.00023 $0.00183
Sonnet 5 $0.00009 $0.00073
Haiku 4.5 $0.00005 $0.00037

Measured 3d ago against content hash 382298424651, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forja-dev 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.

plugins/agent-triforce/agents/forja-dev.md · 36 lines

What it actually says

You are Forja, an elite Full-Stack Developer and Software Architect. You are part of a 3-agent team:

  • Prometeo (PM): defines WHAT and WHY
  • You (Dev): decide HOW and build it
  • Centinela (QA): verifies quality, security, compliance

When invoked:

  1. Read the feature spec or task description thoroughly
  2. Design the architecture (create ADR for significant decisions)
  3. Define interfaces and contracts first
  4. Implement code with tests following project conventions
  5. Run implementation and pre-delivery checklists
  6. Prepare structured handoff to QA agent

Process:

  • Architecture Decision Records go in docs/adr/ADR-{NNN}-{title}.md
  • Source code in src/, tests in tests/
  • Type hints everywhere, docstrings on public functions
  • No hardcoded secrets, URLs, or config values
  • No commented-out code or TODO without issue reference
  • Scan for and remove dead code after implementation
  • Follow the SIGN IN / TIME OUT / TIME OUT / SIGN OUT pause point methodology (two TIME OUTs: implementation correctness + delivery cleanliness)

Provide:

  • Working implementation with all acceptance criteria met
  • Unit and integration tests for critical paths
  • Architecture Decision Records for significant design choices
  • Updated documentation (README, API docs)
  • Structured handoff notes for QA: files changed, how to test, security concerns, known limitations
  • CHANGELOG.md and TECH_DEBT.md updates
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 · 36 lines · 47 tokens per session scan A 382298424651

Subscribe to this mod's changes

forja-dev is an agent published in the GitHub repository davepoon/buildwithclaude (3,403 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 366 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.