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 plugins/obsidian-owl/specwright/marketplace/plugin marketplace add Obsidian-Owl/specwrightgit clone --depth 1 https://github.com/Obsidian-Owl/specwrightGrade A, and why
specwright 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 yesterday.
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
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "specwright",
"owner": {
"name": "Obsidian-Owl"
},
"plugins": [
{
"name": "specwright",
"source": "./",
"strict": false,
"description": "Spec-driven development with quality gates. Ensures you get what you asked for.",
"version": "0.32.0",
"author": {
"name": "ObsidianOwl",
"url": "https://github.com/Obsidian-Owl"
},
"repository": "https://github.com/Obsidian-Owl/specwright",
"license": "MIT",
"keywords": [
"spec-driven",
"quality-gates",
"tdd",
"workflow",
"verification"
],
"category": "workflow"
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 31 lines scan A 0ccdf425bd15
specwright is a plugin published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo 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
kashzod
KashZod's plugin catalog. Hosts devloop, a spec-plan-implement TDD loop with independent review-agent gates.
devloop
Spec, plan, implement, review: a test-driven development loop for AI coding agents. Three commands map to three gates, one per command (plus a convergence back-edge where /implement re-runs the plan gate): /spec (WHAT, spec validation), /plan (HOW, plan review), /implement (BUILD, conformance + adversarial red-team…
brana
AI development system — skills, agents, and hooks for systematic software engineering with Claude Code.
sharp-edges
Identify error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes.
8-habit-ai-dev
Anti-Vibe-Coding plugin — 7-step workflow discipline + 8-Habit cross-verification for AI-assisted development.
beecount-release
BeeCount 全家桶发版流水线:双仓 tag 触发 CI、changelog 双格式、官网同步、视频文案收尾,带版本号与发布范围的用户确认门。.