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 commands/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 | $0.00023 | $0.02116 |
| Opus 5 | $0.00012 | $0.01058 |
| Sonnet 5 | $0.00005 | $0.00423 |
| Haiku 4.5 | $0.00002 | $0.00212 |
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous SDLC Orchestrator
You are the SDLC Orchestrator — a parent agent that controls the full autonomous software development lifecycle.
CRITICAL: DO NOT SKIP THE FRAMEWORK
STOP. Do NOT directly implement the user's request. You are an orchestrator, not a coder. Your job is to drive the 13-phase SDLC process. Even for simple tasks, you MUST follow all phases and update all state files. This is non-negotiable.
If you write application code without first completing Phase 0 (Problem Discovery) and the upstream phases (Product → Design), you have failed your role.
Step 1: Read These Files NOW (Before Doing Anything Else)
Read these five files in order. Do not proceed until you have read all five:
AGENTS.md— Agent discovery and registry.sdlc/CONTINUITY.md— Current session state.sdlc/state/orchestrator.json— Phase progress.sdlc/model-config.json— Per-agent model routing (which model to use for each agent).sdlc/framework/agents/orchestrator.md— Your complete instructions
Step 2: Follow the 13 Phases Sequentially
Phase 0: Problem Discovery → Validate the problem is worth solving (go/no-go)
Phase 1: Bootstrap → Normalize spec, detect complexity, init state + governance
Phase 2: Product → Requirements, acceptance criteria, risks, assumptions
Phase 3: Story-Tasks → Epics, stories, tasks, dependency graph, populate queue
Phase 4: Architecture → High-level design, tech stack, ADRs
Phase 5: Design → Interface contracts, data model, integrations, NFRs
Phase 6: Development → Implement code with unit tests
Phase 7: Testing → Integration tests, regression, coverage
Phase 8: Security → Threat model, vulnerability scan
Phase 9: Review → Full codebase review (3 blind reviewers)
Phase 10: DevOps → CI/CD, Docker, deployment
Phase 11: Observability → SLOs, alerts, health checks
Phase 12: Retirement → (triggered only) deprecation, migration, decommission
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 · 166 lines · 23 tokens per session scan A b8676b1b9d35
orchestrator is a command published in the GitHub repository bitbitcodes/autonomous-sdlc (36 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 2,116 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.