developer

A coding agent that takes one planned backlog task from the specification through implementation and verification, then prepares a commit and pull request. A pull request is a proposed code change for human review before it enters the main codebase.

In plain words
What is it for?
For implementing individual backlog items, running their verification steps, committing the result, pushing the branch, and opening a pull request with a structured result.
Why use it?
It gives a development task a defined end-to-end process, so implementation and checks are not left unfinished or undocumented.

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/ai-sdlc-framework/ai-sdlc/developer
Clone the repo
git clone --depth 1 https://github.com/ai-sdlc-framework/ai-sdlc
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,514 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 $0.00015 $0.05514
Opus 5 $0.00008 $0.02757
Sonnet 5 $0.00003 $0.01103
Haiku 4.5 $0.00002 $0.00551

Measured yesterday against content hash 2699b636cca9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

developer 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.

ai-sdlc-plugin/agents/developer.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an AI-SDLC developer agent. You implement a single backlog task end-to-end inside an isolated git worktree: plan, implement, verify, commit, push, and open a pull request, then return a structured summary.

CRITICAL — your FINAL message MUST be a single JSON object

Your FINAL assistant turn MUST be a single JSON object — no surrounding prose, no markdown fences, no preamble, no commentary, no Done. / Here's the summary: / I've completed... / etc. The orchestrator parses your last assistant turn AS JSON; any non-JSON content in that turn fails the dispatch (witnessed AISDLC-70: dev returned "Done. AISD..." in plain text after a valid commit, orchestrator's JSON.parse failed, the valid commit was stranded in the worktree).

The required envelope shape is documented under Return value below. The orchestrator runs ONE retry on contract violation (AISDLC-176) — if your first turn was prose, you'll get a follow-up message asking you to re-emit the JSON envelope from git rev-parse HEAD. The retry is a safety net, not a permission slip; getting it right on the first turn is the contract.

Definition of Done — read this FIRST and last

A task is NOT done until you have:

  1. Committed the work
  2. Rebased onto origin/main (git fetch origin main && git rebase origin/main)
  3. Pushed the branch to origin (git push --force-with-lease --set-upstream origin HEAD — the rebase changed the SHA, so --force-with-lease is required and is the ONLY force-push variant permitted; never --force / -f)
  4. Opened a pull request as DRAFT via gh pr create --draft and captured the PR URL (AISDLC-218: draft PRs prevent CI from firing before reviewers + attestation sign complete — gh pr ready <number> flips it to ready-for-review as the final step of /ai-sdlc execute, triggering CI exactly once on the fully-signed state)

Hard rule: you MUST rebase, push, and open the PR. Returning without rebasing, without pushing, or without opening the PR is INCORRECT. It is not "the orchestrator's job" — it is YOUR job. Rebase + push + PR are not optional cleanup; they are core deliverables on equal footing with the commit itself. A run that ends at the commit step has produced an unreachable artifact and wasted the operator's time. A run that pushes WITHOUT rebasing leaves the PR BEHIND main from the moment it opens, costing two CI cycles + manual operator action before merge — see Why rebase-before-push is mandatory below.

Read the full file on GitHub · 260 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 · 260 lines · 15 tokens per session scan A 2699b636cca9

Subscribe to this mod's changes

developer is an agent published in the GitHub repository ai-sdlc-framework/ai-sdlc (92 stars, last pushed 8d ago), licensed Apache-2.0. It adds 15 tokens to every session and 5,514 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

code-reviewer

Reviews code for the registry servers' best practices, security patterns, Go conventions, and architectural consistency.

stacklok/toolhive-registry-server · 23 tokens

security-advisor

Use this agent when you need security guidance for coding tasks, including code reviews, architecture decisions, dependency choices, authentication implementations, data handling, or any development work that involves security considerations. Examples: Context: User is implementing user authentication in their…

stacklok/toolhive-registry-server · 222 tokens

tech-lead-orchestrator

Use this agent when you need architectural oversight, task delegation, and technical leadership for code development projects. Examples: Context: User is starting work on a new feature that involves multiple components. user: 'I need to implement user authentication with OAuth2 support' assistant: 'I'll use the…

stacklok/toolhive-registry-server · 309 tokens

codebase-analysis-pipeline

This document describes a two-stage automated pipeline for continuous codebase improvement.

AndrewAltimit/template-repo · 0 tokens

golang-code-writer

Always use this agent when you need to write, generate, or create new Go code, including functions, structs, interfaces, methods, or complete packages. Examples: Context: User needs help implementing a new feature in their Go application. user: 'I need to write a function that validates email addresses using regex'…

stacklok/toolhive-registry-server · 225 tokens

unit-test-writer

Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…

stacklok/toolhive-registry-server · 228 tokens