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/tzachbon/smart-ralphWrote 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/tzachbon/smart-ralph/ralph-speckit)<a href="https://agentmods.dev/plugins/tzachbon/smart-ralph/ralph-speckit"><img src="https://agentmods.dev/badge/plugins/tzachbon/smart-ralph/ralph-speckit/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/tzachbon/smart-ralph/ralph-speckit"><img src="https://agentmods.dev/badge/plugins/tzachbon/smart-ralph/ralph-speckit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ralph-speckit 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": "ralph-speckit",
"version": "0.5.2",
"description": "Spec-driven development using GitHub spec-kit methodology. Constitution-first approach with specify, plan, tasks, and implement phases.",
"author": {
"name": "tzachbon"
},
"license": "MIT",
"keywords": ["ralph", "speckit", "spec-driven", "constitution", "specify", "plan", "tasks", "implement"]
}
What it installs
The manifest is a name and a version. 4 skills, 14 commands, 6 agents, 1 hook travel with it, and installing the plugin installs all of them — 467 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill speckit-workflow A 30 tokens
- Skill smart-ralph A 24 tokens
- Skill communication-style A 26 tokens
- Skill delegation-principle A 30 tokens
- Command start A 12 tokens
- Command status A 6 tokens
- Command cancel A 7 tokens
- Command switch A 3 tokens
- Command implement A 4 tokens
- Command speckit.specify A 13 tokens
- Command speckit.checklist A 13 tokens
- Command speckit.implement A 14 tokens
- Command speckit.clarify A 27 tokens
- Command speckit.analyze A 26 tokens
- Command speckit.plan A 14 tokens
- Command speckit.tasks A 18 tokens
- Command speckit.constitution A 21 tokens
- Command speckit.taskstoissues A 21 tokens
- Agent spec-executor A 29 tokens
- Agent qa-engineer A 20 tokens
- Agent task-planner A 30 tokens
- Agent plan-architect A 26 tokens
- Agent constitution-architect A 25 tokens
- Agent spec-analyst A 28 tokens
- Hook Stop A not measured
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 · 11 lines scan A 031e92c2714e
ralph-speckit is a plugin published in the GitHub repository tzachbon/smart-ralph (559 stars, last pushed 1mo 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
lane-writer
Lane conveyor writer for cursor-agent --plugin-dir only. Not for the IDE.
prd-ce
PRD lifecycle methodology engine: scaffolds PRD/SoT/EPICs to template, drives them to completion with stage skills, governs with hooks + deterministic readiness scoring.
github-loop-engineering
Evidence-gated Loop Engineering control loop that uses GitHub Issues and Projects as durable state, evidence, and handoff through the official GitHub MCP Server.
tsk-add
Helps Claude queue a development task from the current conversation using tsk add.
ai-sdlc-harness marketplace
AI-driven SDLC workflow harness — multi-agent dev with plan → code → review → test → PR.
ooda-loop marketplace
Plugin marketplace listing 1 plugin: ooda-loop.