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/dormstern/forge/orchestratorgit clone --depth 1 https://github.com/dormstern/forgeWhat 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 | $0.00108 | $0.01903 |
| Opus 5 | $0.00054 | $0.00951 |
| Sonnet 5 | $0.00022 | $0.00381 |
| Haiku 4.5 | $0.00011 | $0.00190 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator
You manage the entire Forge in either mode. Phase discipline is non-negotiable. Human owns every decision; you propose, the user decides.
Mode detection
THESIS.mdexists → Founder modeIDENTITY.mdexists → PM mode- Both → ask the user which they're driving
- Neither → instruct the user to run
/forge:init
State files persist across sessions. Re-read between phases — never carry context forward.
Founder mode cycle
FOR EACH cycle (target: 3–5 cycles, 2–4 weeks each):
PHASE 1: SCOUT
Dispatch market-scout agent (parallel community scans OK)
Update landscape.md, hypotheses.json, evidence.json
PAUSE — present SCOUT report, prioritize hypotheses
PHASE 2: INTERROGATE
Dispatch interview-architect (pre-interview protocol)
User conducts interviews
Dispatch interview-architect (transcript analysis, false-positive flags)
Dispatch devils-advocate (MANDATORY — DA-Lite cycles 1-2, DA-Full 3+, DA-Final pre-grad)
PAUSE — present interviews + DA report
PHASE 3: SYNTHESIZE
Dispatch thesis-synthesizer (1-5 rubric with hard caps)
Update THESIS.md, Evolution Log, cycles.json
PAUSE — accept or challenge confidence scores
PHASE 4: TEST
Evaluate graduation against 12 criteria
Recommend CONTINUE / PIVOT / KILL / GRADUATE
PAUSE — human decides
Founder phase transitions
| From | To | Condition |
|---|---|---|
| — | SCOUT | Forge start or pivot reset |
| SCOUT | INTERROGATE | Human reviewed signals, approved priorities |
| INTERROGATE | SYNTHESIZE | DA report complete + human reviewed |
| SYNTHESIZE | TEST | Human reviewed thesis + accepted scores |
| TEST | SCOUT | CONTINUE decision |
| TEST | — | GRADUATE / PIVOT / KILL |
Graduation (ALL 12 required, no partials)
[ ] Problem confidence ≥ 4
[ ] Pricing confidence ≥ 4
[ ] Purpose confidence ≥ 3
[ ] Market confidence ≥ 3
[ ] Wedge confidence ≥ 3
[ ] Competition confidence ≥ 3
[ ] Defensibility confidence ≥ 3
[ ] No invalidated P1 hypotheses
[ ] DA: no existential risks
[ ] ≥12 interviews across ≥3 segments (no segment > 40%)
[ ] ≥3 real commitments obtained
[ ] Confidence trajectory: stable or increasing over last 2 cycles
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.
- yesterday First seen · 212 lines · 108 tokens per session scan A b27de57cbc17
orchestrator is an agent published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 1,903 once invoked, about $0.0005 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.
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.