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/Jartan-LLC/grimoireWrote 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/jartan-llc/grimoire/recursio)<a href="https://agentmods.dev/plugins/jartan-llc/grimoire/recursio"><img src="https://agentmods.dev/badge/plugins/jartan-llc/grimoire/recursio/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/jartan-llc/grimoire/recursio"><img src="https://agentmods.dev/badge/plugins/jartan-llc/grimoire/recursio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
recursio 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 5d 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": "recursio",
"version": "1.1.3",
"description": "Recursive multi-agent development system with TDD -- decomposes projects into waves of parallel nested subagents",
"author": {
"name": "Jartan LLC",
"url": "https://github.com/Jartan-LLC"
}
}
What it installs
The manifest is a name and a version. 5 skills, 4 agents travel with it, and installing the plugin installs all of them — 224 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill recursive-planning A 28 tokens
- Skill recursive-implement A 15 tokens
- Skill recursive-quality A 18 tokens
- Skill recursive-development A 25 tokens
- Skill recursive-execution A 22 tokens
- Agent recursive-reviewer A 28 tokens
- Agent recursive-orchestrator A 34 tokens
- Agent recursive-planner A 25 tokens
- Agent recursive-implementer A 29 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.
- 5d ago Changed a9d8ce0e7d1e
- 1mo ago First seen · 10 lines scan A f08c0e2cce71
recursio is a plugin published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed yesterday), 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
superjawn
Research-augmented fork of obra/superpowers. Ships 13 workflow skills (brainstorming, planning, code review, debugging, verification, worktrees, parallel agents) standalone, with no dependency on the upstream superpowers plugin.
supergraph
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.10.8,<0.11.0 with optional Serena LSP intelligence, 7 specialized subagents, and native Rust CDP browser/API automation. Includes blast-radius planning, test/cycle gates, independent…
testing
Testing — What to test, at which level, and how to keep a suite worth running.
pdlc
Turn AI software engineering into an auditable, on-disk state machine. A staged PDLC workflow (PRD, design, TDD, implement, review, ship, retro) enforces hard contracts — artifacts on disk, per-feature state machine, tests-before-code, objective checks from real command exit codes, single-shot auto-repair — so AI work.
engineering
Engineering workflow skills, review agents, and a /feature pipeline: orientation, planning, test-driven development, systematic debugging, refactoring, error handling, observability, containers, CI pipelines, dependency upgrades, migration planning, incident postmortems, code review, completion verification, and…
rageatc-code-oss
Scale-adaptive software development — TDD, verification, perspective-based review, interface design, and tool capabilities (browser automation, PDFs, YouTube transcripts, local-LLM and Codex delegation).