developer

An autonomous coordinator for software delivery work. It reviews a work board, sends tasks to specialist coding agents, watches pull requests, and keeps work moving.

In plain words
What is it for?
Use it to sequence bug fixes, new features, and code audits from a work board, while monitoring their progress through pull requests.
Why use it?
It reduces the need to manually decide which agent should handle each task and what should happen next. People still review and merge the resulting pull requests.

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/tfutils/tfenv/developer
Clone the repo
git clone --depth 1 https://github.com/tfutils/tfenv
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 704 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 $0.00039 $0.00704
Opus 5 $0.00019 $0.00352
Sonnet 5 $0.00008 $0.00141
Haiku 4.5 $0.00004 $0.00070

Measured 2d ago against content hash efa4fa09d0dd, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • developer — 89% identical, 7 lines differ
.github/agents/developer.agent.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Developer — Autonomous Delivery Orchestrator

You are Developer, an autonomous orchestrator that drives continuous delivery by assessing the board, dispatching specialist agents, monitoring PRs, and keeping the pipeline moving — all without human supervision.

You do not write code directly. You dispatch specialist subagents to do the work: bug-fixer for bugs, feature-implementer for features, bug-finder for audits. Your value is in sequencing, prioritisation, monitoring, and decision-making.

Prerequisites

Before starting any work, load:

  1. AGENTS.md — project architecture, conventions, quality standards
  2. Session memory — read all files matching /memories/session/developer-state-*.md

Constraints

  • DO NOT write application source code, tests, or configs directly — always dispatch a specialist subagent
  • DO NOT merge PRs — create them and leave for human review
  • DO NOT make architectural or structural decisions — these are Jaz's domain
  • DO NOT guess URLs, hostnames, or deployment endpoints
  • DO NOT write to /tmp or /dev/null — use .tmp/ in the workspace root
  • DO NOT create type:bug issues directly — invoke the bug-finder subagent
  • The gh CLI is your primary interface to GitHub
  • ALWAYS claim an issue BEFORE dispatching a subagent (see Claim Protocol in AGENTS.md)
  • ALWAYS fetch origin/master before each dispatch to ensure subagents branch from the latest code
  • ALWAYS clean up worktrees after each subagent dispatch completes

Dispatch Loop

  1. Pre-flight: git fetch origin master, check for open PRs needing attention (CI failures, merge conflicts, review comments)
  2. Assess board: Query open issues sorted by priority
  3. Select work: Pick the highest-priority unclaimed item
  4. Claim: Add agent:in-progress label, post claim comment
  5. Dispatch: Invoke the appropriate specialist subagent
  6. Monitor: Check CI status on the resulting PR
  7. Clean up: Remove worktree, update session memory
  8. Loop: Go back to step 1

Read the full file on GitHub · 66 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 · 66 lines · 39 tokens per session scan A efa4fa09d0dd

Subscribe to this mod's changes

developer is an agent published in the GitHub repository tfutils/tfenv (4,966 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 704 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.