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/fn-opt/dryforgeWrote 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/plugins/fn-opt/dryforge/claude)<a href="https://agentmods.dev/plugins/fn-opt/dryforge/claude"><img src="https://agentmods.dev/badge/plugins/fn-opt/dryforge/claude/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/plugins/fn-opt/dryforge/claude"><img src="https://agentmods.dev/badge/plugins/fn-opt/dryforge/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
claude 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.
What it actually says
{
"name": "dryforge",
"description": "Intent-to-implementation: from a goal, design docs, notes, or a mix, elicit and validate intent into a grounded 3-doc, then orchestrate dependency-aware parallel execution with right-sized review.",
"version": "1.1.1",
"license": "MIT",
"keywords": ["spec", "plan", "intent", "elicitation", "execution", "orchestration", "parallel", "subagent", "tdd", "code-review", "worktree"],
"author": { "name": "fn-opt" }
}
What it installs
The manifest is a name and a version. 3 skills travel with it, and installing the plugin installs all of them — 225 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 9 lines scan A f20edeaa2a3a
claude is a plugin published in the GitHub repository fn-opt/dryforge (141 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
version-sentinel
Hard-blocks dependency additions, bumps, and downgrades until a fresh, source-cited version check is recorded. Supports npm, pip, Poetry/uv, Cargo, and NuGet.
version-sentinel
Hard-blocks dependency additions and version changes until the agent records a WebSearch-verified latest-version check.
security
Threat modeling, security architecture review, incident response, vulnerability management, and access and identity. Reviewer-class: blocking findings are not overrulable by the department under review.
data-analytics
Data governance, warehouse and semantic modeling, business intelligence, and AI/ML governance.
revenue
Outbound, sales enablement, revenue operations, pricing and packaging, activation, retention, and referrals.
markifact marketplace
Run Google Ads, Meta Ads, GA4, Shopify, and 50+ more platforms from Claude. 1000+ operations with human-in-the-loop on every write.