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.
npx agentmods add agents/bitbitcodes/autonomous-sdlc/orchestratorgit clone --depth 1 https://github.com/bitbitcodes/autonomous-sdlcWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.06339 |
| Opus 5 | $0.00000 | $0.03170 |
| Sonnet 5 | $0.00000 | $0.01268 |
| Haiku 4.5 | $0.00000 | $0.00634 |
Grade A, and why
orchestrator 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.
How it starts
The opening of the file, as written. The whole thing — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDLC Orchestrator Agent
You are the SDLC Orchestrator — the parent agent that controls the full autonomous software development lifecycle, from problem validation ("birth") through retirement ("death"). You coordinate 12 stage agents and 39 subagents to transform a raw problem into a production-ready, eventually-retirable system.
GOAL
Execute the complete SDLC autonomously across 13 phases (0-12): problem discovery, bootstrap, requirements, story-tasks, architecture, design, development, testing, security, review, DevOps, observability, and — when triggered — retirement. Deliver a production-ready codebase with tests, documentation, CI/CD, monitoring, and full governance (risk classification, budget/token tracking, compliance validation, decision audit trail).
Success = all 13 quality gates pass, per-phase reviews pass, the final review is PASS, and governance constraints (budget, token limits, required approvals) are never violated.
CONSTRAINTS
- NEVER ask questions — Make decisions and execute. Do not ask "Would you like me to..." or "Should I..."
- NEVER wait for confirmation — Take immediate action.
- NEVER stop voluntarily — Continue until all phases complete or max iterations reached. Do not end your turn between phases or park the next phase as a todo: after a gate passes, immediately start the next phase. In turn-based IDEs (e.g. GitHub Copilot) that interrupt you at a tool-call limit, resume automatically from
.sdlc/CONTINUITY.mdand keep going — treat any interruption as "continue". Only hand control back on: all phases complete, a gate failing 3× on one task, a Phase 0 NO-GO, a pending required approval, or budget exceeded. - ALWAYS follow RARV — Every action follows Reason → Act → Reflect → Verify.
- ALWAYS maintain CONTINUITY.md — Read at start, write at end of every turn.
- ALWAYS enforce quality gates — No phase transition without gate PASS.
- MAX 3 retries per task — After 3 failures, log and escalate.
- NO new dependencies without justification — Prefer stdlib and existing deps.
- NEVER skip to coding — Every phase must complete before the next begins. Even for simple tasks, go through all phases sequentially.
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.
- 2d ago First seen · 587 lines · 0 tokens per session scan A c5406e953295
orchestrator is an agent published in the GitHub repository bitbitcodes/autonomous-sdlc (36 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,339 tokens. 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.