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/ribeirogab/specwrightWrote 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/ribeirogab/specwright/sw)<a href="https://agentmods.dev/plugins/ribeirogab/specwright/sw"><img src="https://agentmods.dev/badge/plugins/ribeirogab/specwright/sw/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/ribeirogab/specwright/sw"><img src="https://agentmods.dev/badge/plugins/ribeirogab/specwright/sw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sw 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": "sw",
"version": "2026.8.8",
"description": "The specwright ladder for Claude Code and Codex: init, propose, plan, implement, review, archive, ship, and delivery.",
"author": {
"name": "Gabriel Ribeiro"
}
}
What it installs
The manifest is a name and a version. 8 skills, 8 commands, 2 agents travel with it, and installing the plugin installs all of them — 1,040 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill review A 107 tokens
- Skill delivery A 86 tokens
- Skill plan A 76 tokens
- Skill implement A 79 tokens
- Skill init A 94 tokens
- Skill ship A 76 tokens
- Skill archive A 65 tokens
- Skill propose A 73 tokens
- Command plan A 41 tokens
- Command review A 38 tokens
- Command archive A 29 tokens
- Command delivery A 38 tokens
- Command implement A 34 tokens
- Command init A 40 tokens
- Command propose A 33 tokens
- Command ship A 37 tokens
- Agent sw-change-owner A 50 tokens
- Agent sw-reviewer A 44 tokens
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 6324641ad152
sw is a plugin published in the GitHub repository ribeirogab/specwright (3 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 2026-08-31.
Other plugins, from other repositories
specclaw-sync
Tracker sync add-on for specclaw: GitHub issues, Azure DevOps boards and PRs, Jira.
project-workflow marketplace
Plugin marketplace listing 1 plugin: project-workflow.
dev-workflow
Plan features with structured PRDs, checkpoint progress, and resume across sessions.
manager
Product and project management discipline for the NVZver marketplace. Agents: product-manager — shapes vague ideas into structured draft pitches and returns their full content + pending human gates (writes no files); project-manager — stewards the roadmap, recommends what to build next with dependency/risk/value…
shipspec
Spec-driven development for big features. When features get too big, plan mode gets too vague—leading to hallucinations during implementation. ShipSpec replaces vague plans with structured PRDs, technical designs, and ordered tasks that keep Claude grounded.
peachflow
Your AI development team in a CLI. Uses a graph-based work item system with epics, stories, and tasks. Sprint-based implementation with git worktrees.