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/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-research)<a href="https://agentmods.dev/commands/razaib-khan/forgeweave/forge-research"><img src="https://agentmods.dev/badge/commands/razaib-khan/forgeweave/forge-research/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/razaib-khan/forgeweave/forge-research"><img src="https://agentmods.dev/badge/commands/razaib-khan/forgeweave/forge-research.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 | $0.00016 | $0.00541 |
| Opus 5.5 | $0.00006 | $0.00216 |
| Sonnet 5.5 | $0.00003 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
forge-research 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 2mo 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Research
Triggers the deep-research skill which internally runs a 6-stage pipeline: planner → parallel researchers → validator → synthesizer → raw output → skill conversion.
The caller only sees the finished report and skill path. All pipeline stages are internal.
Usage: /forge-research <topic> [--depth=<quick|standard|deep>] [--focus=<usage|architecture|comparison|general>] [formatted|unformatted] [skill|no-skill]
Behavior
- Triggers the deep-research skill with the topic and options
- Output format:
formatted(default): Produces a well-organized, structured markdown report with sections, code examples, and citationsunformatted: Produces raw scraped output only — one markdown file per source URL with minimal processing
- Skill generation:
skill(default): Also generates a reusable SKILL.md in.opencode/skills/<topic>/no-skill: Skips skill generation — report only
- Progress is reported via chat messages during execution
Internal Pipeline (hidden from caller)
| Stage | Component | What it does |
|---|---|---|
| Plan | Planner agent | Decompose topic into subtopics + seed URLs (uses Playwright MCP for JS-rendered pages) |
| Research | Research agents (×N parallel) | Crawl URLs, extract code examples (Playwright MCP for JS content) |
| Validate | Validator agent | Cross-check claims, remove hallucinations |
| Synthesize | Synthesizer agent | Merge into final structured report |
| Raw Output | Output writer | Save raw scraped data as research/<slug>-raw/*.md |
| Skill Conversion | Skill builder | Convert raw findings into industry-grade .opencode/skills/<topic>/SKILL.md |
Rules
- All 6 stages run automatically — no manual intervention
- Sources must be official docs, API refs, usage guides only
- NO blog posts, NO changelogs, NO marketing pages
- Every claim must have a traceable source URL
- Progress is reported via chat messages during execution
Examples
/forge-research Next.js 16 caching --depth=deep --focus=usage formed
/forge-research Next.js 16 caching unformatted no-skill
/forge-research Python 3.14 pattern matching formated no-skill
/forge-research React Server Components formated skill
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.
- 2mo ago First seen · 53 lines · 16 tokens per session scan A 646da2578bbb
forge-research is a command published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 541 once invoked, about $0.0001 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 2026-08-31.
forge-research compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| forge-researchRazaib-khan/ForgeWeave | Command | 1 | 4mo ago | MIT | A | 16 | Claude Code |
| aligndsswift/ion | Command | 5 | yesterday | MIT | A | 51 | Claude Code |
| squashdsswift/ion | Command | 5 | yesterday | MIT | A | 25 | Claude Code |
| resolve-dependabot-prsdsswift/ion | Command | 5 | yesterday | MIT | A | 35 | Claude Code |
| update-vocabularydsswift/ion | Command | 5 | yesterday | MIT | A | 19 | Claude Code |
| autoInsajin/autopus-adk | Command | 111 | 1mo ago | MIT | A | 13 | Claude Code |
| auto-canaryInsajin/autopus-adk | Command | 111 | 1mo ago | MIT | A | 20 | Claude Code |