ragcode-agents

A workflow tool for coordinating multiple AI agents, such as Codex, Claude, or Gemini, through ordered or parallel stages. A workflow is a defined sequence of tasks with review steps and limited fix loops.

In plain words
What is it for?
Use it to turn a collaboration request into a validated workflow, assign agents to roles, run stages in sequence or parallel, and add review gates.
Why use it?
It organizes collaboration when different agents need distinct roles, such as planning, implementation, and review. It also records the workflow run and preserves explicitly assigned responsibilities.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/marshalleriksen-neura/ragcode/ragcode-agents
Any agent
npx skills add MarshallEriksen-Neura/ragcode --skill ragcode-agents
Clone the repo
git clone --depth 1 https://github.com/MarshallEriksen-Neura/ragcode

Made for: Claude Code, Codex.

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,374 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00096 $0.01374
Opus 5 $0.00048 $0.00687
Sonnet 5 $0.00019 $0.00275
Haiku 4.5 $0.00010 $0.00137

Measured 3d ago against content hash 0253d9b7b14f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ragcode-agents 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 3d 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.

integrations/codex/skills/ragcode-agents/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RagCode Agents

RagCode orchestrates multiple AI agents (codex, claude, gemini, grok, or any CLI configured in .ragcode/agents/agents.json) through a validated DAG workflow. A user describes a collaboration pattern in natural language; you generate a workflow spec as JSON data; RagCode validates and executes it with review gates, bounded fix loops, and an append-only run ledger.

This is NOT a fixed "claude + codex parallel consult" command. The architecture supports arbitrary role-to-agent assignment, serial and parallel stages, review/fix loops, and explicit write permissions.

When to use

  • User describes a multi-agent collaboration → generate a workflow spec.
  • User wants plan → implement → review with different agents → workflow with a review gate.
  • User names specific agents for specific roles ("let Gemini plan, Codex implement") → preserve their assignment.
  • User wants to run a previously-defined workflowragcode agents run.

Core rules (follow strictly)

  1. Preserve the user's explicit role-to-provider assignment. If they say "Gemini plans, Codex implements", do not swap to "Claude plans, Codex implements".
  2. Generate workflow JSON, not prose. The spec is data; RagCode validates it.
  3. Read-only stages (plan, breakdown, review, verify) use "mode": "read_only".
  4. Implementation stages (implement, fix) use "mode": "write" and MUST declare writePolicy with allowedPaths.
  5. Add a review gate with onFail + maxLoops (1..10) whenever a reviewer is named.
  6. Always validate before run: ragcode agents validate . --workflow <path>.
  7. Prefer --dry-run first unless the user explicitly asked to execute.
  8. Use presets only when the user did not specify roles.

Workflow spec (v1)

A spec is JSON with version, name, description, agents (role → provider mapping), workflow (ordered DAG nodes), and optional finalGate. Each node declares id, agent, kind, mode, dependsOn, input/output, and optional gate or writePolicy.

Read the full file on GitHub · 96 lines

Files

What ships with it

4 files beside SKILL.md 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.

Changes

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.

  1. 3d ago First seen · 96 lines · 96 tokens per session scan A 0253d9b7b14f

Subscribe to this mod's changes

ragcode-agents is a skill published in the GitHub repository MarshallEriksen-Neura/ragcode (11 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,374 once invoked, about $0.0005 per session on Opus 5. 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.

Related

Other skills, from other repositories

seller-research

Use when researching a merchant, storefront, marketplace seller, or merchant of record for a buying decision, especially when identity, refund terms, fulfillment, counterfeit risk, domain history, or independent buyer outcomes are uncertain.

cinderline/northcinder · 46 tokens

claude-md-improver

Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.

mrclrchtr/supi · 39 tokens

pi-tui-design

Create distinctive, crafted TUI components for pi using @earendil-works/pi-tui and @earendil-works/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements, game-like interfaces, or any visual TUI work inside pi…

mrclrchtr/supi · 141 tokens

update-package-readme

Update one SuPi package README and its direct user-facing Markdown references from installed Pi docs and verified package evidence.

mrclrchtr/supi · 27 tokens

claude-md-revision

Record durable, project-specific learnings from the current session in CLAUDE.md, .claude.local.md, or AGENTS.md—not general documentation, session summaries, or repo-wide audits.

mrclrchtr/supi · 45 tokens

pi-upgrade

Check for available upgrades to the pi coding agent framework by comparing the current @earendil-works/pi- or legacy @mariozechner/pi- version in package.json against releases on earendil-works/pi. Use this skill whenever the user asks to upgrade pi, update pi, check pi changelogs/releases, or migrate off the…

mrclrchtr/supi · 90 tokens