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 Tholem-AI/Tholem-Hermes-Kit --skill riper-orchestratorgit clone --depth 1 https://github.com/Tholem-AI/Tholem-Hermes-KitWrote 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/tholem-ai/tholem-hermes-kit/riper-orchestrator)<a href="https://agentmods.dev/skills/tholem-ai/tholem-hermes-kit/riper-orchestrator"><img src="https://agentmods.dev/badge/skills/tholem-ai/tholem-hermes-kit/riper-orchestrator/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/tholem-ai/tholem-hermes-kit/riper-orchestrator"><img src="https://agentmods.dev/badge/skills/tholem-ai/tholem-hermes-kit/riper-orchestrator.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 | $0.00034 | $0.04668 |
| Opus 5 | $0.00017 | $0.02334 |
| Sonnet 5 | $0.00007 | $0.00934 |
| Haiku 4.5 | $0.00003 | $0.00467 |
Grade A, and why
riper-orchestrator 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 10d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
riper-orchestrator
Overview
Coordinate RIPER phase execution using role-specific agents and evidence-first handoffs. This skill guides the parent agent through structured delegation to research, planning, execution, and review phases.
Important: The orchestrator is a leaf skill — it cannot call delegate_task itself. It provides phase-by-phase instructions that guide the parent agent to invoke the correct subagent at each step.
When to Use
- Use for non-trivial work that benefits from explicit phase handoffs and checkpoints.
- Use when you need to delegate scoped tasks to subagents with clear role boundaries.
- Always trigger for multi-file edits, physics/application logic changes, or anything that touches shared state.
- Don't use for simple tasks (< 20 lines, single file) — just execute directly.
Trigger phrases (MANDATORY — these are non-negotiable)
When the user says any of the following, you MUST follow the complete RIPER flow with all four agents:
- "full riper" or "riper orchestration"
- "use riper" or "follow riper"
- "use agents" or "use subagents" or "delegate"
- "use the associated skills" or "use all the skills"
These phrases mean the user explicitly wants the full phase flow. Skipping any phase when these are present is a process violation.
Mandatory close process
After review phase completes and before declaring work done, you MUST:
- Load
documentation-maintainer— Update ROADMAP.md, docs/File-Structure-Reference.md, docs/Project-Constraints.md, README.md to reflect implementation changes. These are always-on per AGENTS.md governance rules 4, 5, 7. - Load
roadmap-updater— Reconcile ROADMAP.md checkpoints with completed work. Add new checkpoints, update status progression, preserve decision context.
This is NOT optional. AGENTS.md governance rule 4 states "Keep ROADMAP.md and relevant docs aligned with actual implementation state" and rule 5 states "Keep docs/File-Structure-Reference.md aligned." These are always-on governance rules, not conditional tasks.
What ships with it
10 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.
- references/browser-physics-verification.md 7.8 KB
- references/chamber-diff-parsing-patterns.md 2.8 KB
- references/file-search-protocol.md 2.2 KB
- references/game-loop-state-debugging.md 1.9 KB
- references/hi-dpi-canvas-rendering.md 3.0 KB
- references/kit-hygiene-tool-fallbacks.md 3.7 KB
- references/magical-wall-debugging.md 4.0 KB
- references/one-way-platform-and-entity-landing.md 5.5 KB
- references/process-audit-2026-05-16.md 1.6 KB
- references/riper-pitfalls-html-canvas-js-games.md 26 KB
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.
- 10d ago First seen · 244 lines · 34 tokens per session scan A babad68a47d7
riper-orchestrator is a skill published in the GitHub repository Tholem-AI/Tholem-Hermes-Kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 4,668 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…