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/razaib-khan/forgeweave/forge-startgit clone --depth 1 https://github.com/Razaib-khan/ForgeWeaveWrote 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/razaib-khan/forgeweave/forge-start)<a href="https://agentmods.dev/commands/razaib-khan/forgeweave/forge-start"><img src="https://agentmods.dev/badge/commands/razaib-khan/forgeweave/forge-start.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00421 |
| Opus 5 | $0.00010 | $0.00211 |
| Sonnet 5 | $0.00004 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
forge-start 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 3d 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.
What it actually says
/forge-start — Context Launcher
AGENTS.md is the primary context source. If you haven't read it yet, read it now. This file is a quick-reference supplement.
Available Commands
| Command | Purpose |
|---|---|
forge init --tui <name> |
Scaffold project for OpenCode/Claude/Qwen/Gemini |
forge doctor |
Check Python 3.14+, templates, dependencies |
/forge-search <query> |
Single web search — quick API lookups, error fixes |
/forge-research <topic> |
6-stage deep research pipeline → report + skill |
Key Files
| File | Purpose |
|---|---|
AGENTS.md |
Primary context — global rules, auto-detection, skills, subagents |
skills/<name>/SKILL.md |
Domain expertise — load when task matches skill trigger |
research/ |
Research output (gitignored) |
Available Skills
| Skill | Use When... |
|---|---|
skill-builder |
Creating or improving any skill |
playwright-mcp |
Browser automation, JS pages |
deep-research |
Comprehensive multi-source research |
web-research |
Fetching URLs for clean content |
quick-research |
Simple factual questions |
architecture-designer |
System design decisions |
code-builder |
Scaffolding new modules |
test-generator |
Writing tests |
refactor-engine |
Code improvement |
debugger |
Debugging methodology |
validation-engine |
Quality assurance |
Standards
- Python 3.14+ required
forge initcopies templates into project- Skills follow SKILL.md + scripts/ + references/ + evals/ layout
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.
- 3d ago First seen · 49 lines · 20 tokens per session scan A 0b3a3233881d
forge-start is a command published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 421 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 2026-08-31.
Other commands, from other repositories
agentlas-cloud
Staff a task only from the signed-in owner's Agent Cloud agents.
agentlas-local
Staff a task only from Agentlas agents registered on this machine.
issue-amend
Re-snapshot the active issue's scope from the spec, clear verified and reviewed receipts, and record the change as a permanent amendment.
os-meeting
快速创建和管理AI团队会议.
q-research
Read the research-mode skill's SKILL.md for the full ruleset before proceeding. Follow all constraints, the source lookup cascade, the token budget, and the "what counts as cited" rules exactly.
create-pr
Push the current branch and open a pull request into main with a structured description derived from the branch's commits and issue references.