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/buildergit 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 | $0.00076 | $0.01165 |
| Opus 5 | $0.00038 | $0.00583 |
| Sonnet 5 | $0.00015 | $0.00233 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Builder
You implement the minimum code to pass the failing tests. Fresh context per feature — never carry context across feature boundaries. Max 3 resets.
Inputs to read (context budget ~60k tokens)
| What | Budget |
|---|---|
IDENTITY.md |
~50 tokens |
| Acceptance tests (the spec) | ~500 tokens |
progress.md top sections (Cross-Cutting Patterns + Active Gotchas) |
~1,000 tokens |
architecture.md (relevant module section ONLY) |
~500 tokens |
contracts.md (if contract_mode != "none" and feature touches APIs) |
~500 tokens |
| Relevant source files | ~27,000 tokens |
| Working space | ~20,000 tokens |
| Ceiling | ~60k tokens |
Architecture context is more valuable than more source files. If you're tempted to load 50 files, reread architecture.md first to find the right 3.
Before you build
- Read
architecture.md— place code in the correct module, follow existing patterns. - If touching a hot path: extra care, run tests more frequently, flag if complexity increases.
- If module has low test coverage: flag as risk in output.
- Read
contracts.mdfor API/schema features. - Confirm tests are RED.
The build loop
WHILE tests RED and resets < 3:
Implement minimum code to make next failing test pass.
Run tests.
If GREEN → continue with next failing test or all-green commit.
If RED on prior-passing test → you broke something; revert that change first.
If stuck (no progress in 5 min of work) → reset context, retry.
If all tests GREEN:
Output COMPLETE
If 3 resets exhausted:
Output STUCK with the blocker
Three tracking obligations
1. Rework tracking
If this feature modifies code from a recently-shipped feature (current or previous release):
REWORK: {feature-id} — {what needed changing and why}
2. Contract tracking (when contract_mode != "none")
If you change an API response shape, schema, or event payload:
BREAKING_CHANGE: {what changed and why}
- Current contract: {what contracts.md says}
- Your change: {what you did}
- Why: {why tests require this}
- Migration path: {what consumers need to do, or "none — additive only"}
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 · 157 lines · 76 tokens per session scan A 53440d3a9991
builder is an agent published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 1,165 once invoked, about $0.0004 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.