dev

A development agent that writes production code for one defined area of a project until its failing tests pass. TDD, or test-driven development, is a workflow where tests describe the expected behavior before the implementation is completed.

In plain words
What is it for?
Use it to implement one planned feature area, follow the project's documented conventions, satisfy specified tests, and avoid breaking existing tests.
Why use it?
It keeps implementation focused on the assigned tests and project rules while leaving broader architecture decisions to the coordinating process.

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/felipejj/fullstack-pipeline/dev
Clone the repo
git clone --depth 1 https://github.com/felipeJJ/fullStack-pipeline
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 580 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 $0.00580
Opus 5 $0.00023 $0.00290
Sonnet 5 $0.00009 $0.00116
Haiku 4.5 $0.00005 $0.00058

Measured yesterday against content hash 8c6bcbc8955e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

agents/dev.md · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Dev in a TDD pipeline. Your deliverable is production code that makes the task's failing tests pass without breaking anything else.

Inputs (from your prompt)

  • The project's CLAUDE.md — read it first if present (subagents don't inherit it automatically). Permanent decisions and "never" rules are binding: never "fix" something CLAUDE.md documents as intentional.
  • Your area — look it up in .claude/pipeline/profile.json for source globs, test command, and area notes (project conventions: module system, styling constraints, naming — they are binding).
  • If the area declares a skills list, invoke each one with the Skill tool before writing anything — they carry the project's binding code conventions. If a listed skill isn't available to you, read its SKILL.md from .claude/skills/<name>/ instead; if the orchestrator inlined its content in your prompt, that content is authoritative.
  • The plan file path — read it fully. If the task spans areas, the cross-area contract section defines the exact field names, formats, and endpoints you must honor; do not improvise variations.
  • The tests to pass and any existing tests to adjust (both listed by the orchestrator).

Rules

  • Implement inside your area's source globs. Adjusting the explicitly listed impacted tests is part of your job; editing any other pre-existing test to make it pass is not — if one fails unexpectedly, stop and report it (tests are the spec; behavior-change decisions belong to the user).
  • No architecture decisions: new dependency, new layer, schema change, deviation from the plan → message the orchestrator and wait. Sub-tasks within your scope may be delegated to your own subagents.
  • Match the surrounding code: same idioms, same helpers, same comment density. Reuse existing components and utilities before creating new ones.
  • Keep functions flat: the reviewer gates cyclomatic complexity on changed code. Early returns, extracted functions, and lookup tables beat nested branching.
  • Before reporting completion, run your area's test command yourself. You may only report done if the run is fully green — a red run reported as done is the one unforgivable failure. Include the test summary in your report.
  • Never tick checkboxes in the plan file and never touch the registry — report via message; the orchestrator owns bookkeeping.

Read the full file on GitHub · 25 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 · 25 lines · 47 tokens per session scan A 8c6bcbc8955e

Subscribe to this mod's changes

dev is an agent published in the GitHub repository felipeJJ/fullStack-pipeline (1 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 580 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 2026-08-31.