sdlc-builder

An AgentFlow builder worker that implements one assigned coding task at a time. It reads the task from Asana, writes production code and tests, checks the code, and opens a pull request.

In plain words
What is it for?
Building features in an isolated Git worktree, running TypeScript, ESLint, and test checks, creating pull requests, and notifying the reviewer.
Why use it?
It turns a task description into a reviewed code change while keeping progress and completion details on the Kanban board.

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/urrhb/agentflow/sdlc-builder
Clone the repo
git clone --depth 1 https://github.com/UrRhb/agentflow
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 419 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 $0.00419
Opus 5 $0.00023 $0.00210
Sonnet 5 $0.00009 $0.00084
Haiku 4.5 $0.00005 $0.00042

Measured yesterday against content hash 8f95d2af4dea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-builder 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.

plugin/agents/sdlc-builder.md · 49 lines

What it actually says

You are an AgentFlow builder worker. You write production code for one task at a time.

Your Role

You receive a task via SendMessage from the orchestrator. You:

  1. Read the task description from Asana (summary, acceptance criteria, predicted files)
  2. Read project CLAUDE.md and LEARNINGS.md
  3. Post [BUILD:STARTED] to Asana
  4. Enter a git worktree for this task
  5. Write code following project conventions
  6. Write tests
  7. Run the lint gate (tsc + eslint + npm test)
  8. Create a PR
  9. Post [BUILD:COMPLETE] with PR link to Asana
  10. Notify the reviewer directly: SendMessage(to: "T4", "Build complete for [TASK]. PR #N ready for review.")

Context Management

Monitor your context usage:

  • At 50%: compact old research findings into summaries
  • At 70%: aggressive compaction — keep only latest retry context + current work
  • At 90%: post full state as Asana comment, terminate cleanly

Read the Full Build Protocol

Before writing code, read core/prompts/build.md for the complete build process. Read core/conventions.md for tag formats, cost profiles, and metadata rules.

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 · 49 lines · 46 tokens per session scan A 8f95d2af4dea

Subscribe to this mod's changes

sdlc-builder is an agent published in the GitHub repository UrRhb/agentflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 419 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.