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.
git clone --depth 1 https://github.com/LucasDuys/forgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/lucasduys/forge/help)<a href="https://agentmods.dev/commands/lucasduys/forge/help"><img src="https://agentmods.dev/badge/commands/lucasduys/forge/help/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/lucasduys/forge/help"><img src="https://agentmods.dev/badge/commands/lucasduys/forge/help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00004 | $0.00627 |
| Opus 5.5 | $0.00002 | $0.00251 |
| Sonnet 5.5 | $0.00001 | $0.00125 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
help 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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Help
Display the following help text to the user:
Commands
/forge brainstorm [topic] — Turn an idea into concrete specs
--from-code— Generate specs from existing codebase--from-docs path/— Generate specs from PRDs, API docs, research files
/forge plan — Decompose specs into task frontiers
--filter <name>— Only plan a specific spec--depth quick|standard|thorough— Set task granularity
/forge execute — Run the autonomous implementation loop
--autonomy full|gated|supervised— Set pause behavior--max-iterations N— Safety cap on loop iterations--token-budget N— Max tokens to spend--depth quick|standard|thorough— Override task depth
/forge resume — Continue after context reset or interruption
/forge backprop "bug description" — Trace a bug back to a spec gap
--from-test path/— Trace from a failing test
/forge status — Show current progress and budget
/forge review-branch — Review an unmerged branch before merging
--base main— Base branch to diff against--spec path/— Spec file for acceptance criteria verification--depth quick|standard|thorough— Review depth--fix— Auto-fix critical issues--comment— Post results as GitHub PR comment
/forge setup-tools — Detect and install CLI tools that enhance Forge
/forge help — Show this help text
Quick Start
/forge brainstorm "build a REST API for task management"/forge plan/forge execute --autonomy gated
Configuration
Edit .forge/config.json to customize autonomy, depth, token budget, multi-repo setup, and circuit breaker thresholds.
Token Reduction Kill Switch
Set FORGE_TOKEN_OPT=0 to disable Wave 2 cache extensions and revert to the original 6-pattern, flat-120s-TTL behavior. All other Wave 2 additions (mtime keying, HEAD pinning, stats logging) also disable. Default is on.
The same FORGE_TOKEN_OPT=0 flag also disables the Wave 3 token-reduction surfaces: the broader output filter, the router's per-phase effort/max_tokens policy, and the first-run wizard banner. Wave 1 instrumentation extras (capture, usage_actual.* ledger keys) bypass too, leaving the v1-shape ledger. This is the single end-to-end rollback contract across all three waves; the wizard prints the same flag on first run.
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.
- 1mo ago First seen · 56 lines · 4 tokens per session scan A 28fd9ed2b345
help is a command published in the GitHub repository LucasDuys/forge (56 stars, last pushed 3mo ago), licensed MIT. It adds 4 tokens to every session and 627 once invoked, about $0.0000 per session on Opus 5.5. 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
cost-optimize
Reduce cloud costs across AWS, Azure, and GCP through rightsizing, reserved and spot capacity, storage tuning, and cost monitoring.
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
critique-screen
Run all seven visual critiques on a screen and output a prioritised fix list.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
doc-changelog
Generation and maintenance of the project changelog.