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 skills add MarshallEriksen-Neura/ragcode --skill ragcode-agentsgit clone --depth 1 https://github.com/MarshallEriksen-Neura/ragcodeWrote 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/skills/marshalleriksen-neura/ragcode/ragcode-agents)<a href="https://agentmods.dev/skills/marshalleriksen-neura/ragcode/ragcode-agents"><img src="https://agentmods.dev/badge/skills/marshalleriksen-neura/ragcode/ragcode-agents/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/skills/marshalleriksen-neura/ragcode/ragcode-agents"><img src="https://agentmods.dev/badge/skills/marshalleriksen-neura/ragcode/ragcode-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.01374 |
| Opus 5.5 | $0.00038 | $0.00550 |
| Sonnet 5.5 | $0.00019 | $0.00275 |
| Haiku 4.5 | $0.00010 | $0.00137 |
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 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.
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 workflow →
ragcode agents run.
Core rules (follow strictly)
- Preserve the user's explicit role-to-provider assignment. If they say "Gemini plans, Codex implements", do not swap to "Claude plans, Codex implements".
- Generate workflow JSON, not prose. The spec is data; RagCode validates it.
- Read-only stages (
plan,breakdown,review,verify) use"mode": "read_only". - Implementation stages (
implement,fix) use"mode": "write"and MUST declarewritePolicywithallowedPaths. - Add a review gate with
onFail+maxLoops(1..10) whenever a reviewer is named. - Always validate before run:
ragcode agents validate . --workflow <path>. - Prefer
--dry-runfirst unless the user explicitly asked to execute. - 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.
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.
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 · 96 lines · 96 tokens per session scan A 0253d9b7b14f
ragcode-agents is a skill published in the GitHub repository MarshallEriksen-Neura/ragcode (11 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 1,374 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
caveman
Opt-in ultra-compressed OUTPUT style for OMK — port of JuliusBrussee/caveman (MIT, pin 0d95a81). Cuts output tokens 65% (measured, range 22-87%) by speaking terse while keeping technical terms, code, errors, API names, CLI commands byte-exact. OUTPUT ONLY: 0% input/context/thinking reduction; adds 1-1.5k input tokens…
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.
omk-computeruse
Route OMK computer-use and Neo tasks by verified tool and model capabilities, without a second orchestrator. Use for native desktop apps, WSL-to-Windows experiments, browser sessions, site previews, screenshots, mouse/keyboard input, structured web extraction, or questions about Neo skills and MCP setup availability.
omk-engine
Project-local OMK operating profile. Use when configuring this repository's OMK workflow, selecting a small skill set, bootstrapping readiness, or routing agent, MCP, hook, and documentation work.
ponytail-gain
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".
context7-mcp
Fetch current library and framework documentation through the Context7 MCP server instead of answering from training data, with a hard cap of three Context7 calls per question, an explicit CONTEXT7UNAVAILABLE block on quota or rate-limit failure, and a TTL + ETag-revalidated disk cache (scripts/lib/doc-fetch-cache.sh)…