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-specum)<a href="https://agentmods.dev/plugins/tzachbon/smart-ralph/ralph-specum"><img src="https://agentmods.dev/badge/plugins/tzachbon/smart-ralph/ralph-specum/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-specum"><img src="https://agentmods.dev/badge/plugins/tzachbon/smart-ralph/ralph-specum.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ralph-specum 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-specum",
"version": "4.12.2",
"description": "Spec-driven development with task-by-task execution. Research, requirements, design, tasks, autonomous implementation, and epic triage for multi-spec feature decomposition.",
"author": {
"name": "tzachbon"
},
"license": "MIT",
"keywords": ["ralph", "spec-driven", "research", "requirements", "design", "tasks", "autonomous", "loop", "epic", "triage"]
}
What it installs
The manifest is a name and a version. 3 skills, 11 commands, 7 agents travel with it, and installing the plugin installs all of them — 593 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill interview-framework A 44 tokens
- Skill spec-workflow A 91 tokens
- Skill reality-verification A 81 tokens
- Command help A 11 tokens
- Command index A 0 tokens
- Command new A 7 tokens
- Command refactor A 0 tokens
- Command feedback A 12 tokens
- Command requirements B 0 tokens
- Command tasks B 0 tokens
- Command design B 0 tokens
- Command research B 0 tokens
- Command triage B 0 tokens
- Command prototype B 6 tokens
- Agent spec-reviewer A 68 tokens
- Agent research-analyst A 57 tokens
- Agent architect-reviewer A 49 tokens
- Agent product-manager A 45 tokens
- Agent refactor-specialist A 53 tokens
- Agent triage-analyst A 51 tokens
- Agent prototype-builder A 18 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 Changed 8dc767fc5fb1
- 1mo ago First seen · 11 lines scan A e7288ef37ee0
ralph-specum 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
credential-brokers
Your credentials stay out of the repo and out of the agent's context. credbroker resolves them in-process, sso-broker handles the browser cookie dance, and an LLM-cooperative credential-setup skill walks you through the first time.
forgedock
Autonomous AI development pipeline that uses GitHub as a structured knowledge graph for Claude Code agents. Adds /work-on, /review-pr, /quality-gate, /orchestrate, and 20+ pipeline commands.
lanes-bridges
Bridge Lanes with GitHub and Linear: import issues, batch-spawn a session per ticket, and post results back upstream. Split out of lanes-desktop in 0.7.0.
bestpractice
Enforcement, memory and parallel-session coordination for solo founders running several Claude Code sessions on one repository.
agent-evolutions
Genetic exploration of solution spaces for AI coding agents — gather a verifiable objective, evolve variants, apply the winner.
ooda-loop marketplace
Plugin marketplace listing 1 plugin: ooda-loop.