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 genudo-ai/genudo_mcp --skill instruction-guidesgit clone --depth 1 https://github.com/genudo-ai/genudo_mcpWrote 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/genudo-ai/genudo_mcp/instruction-guides)<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/instruction-guides"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/instruction-guides/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/genudo-ai/genudo_mcp/instruction-guides"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/instruction-guides.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 | $0.00071 | $0.01942 |
| Opus 5 | $0.00036 | $0.00971 |
| Sonnet 5 | $0.00014 | $0.00388 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
instruction-guides 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 11d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Genudo Instruction Authoring Guides
Follow these when writing or rewriting any instruction field. The safe
load → mirror → stage → diff → confirm → push → record workflow lives in the
editing-playbook skill — run that one for the process, this one for the content.
Real fields: pipeline persona + instructions (via list_pipelines /
update_pipeline); stage instructions + enter_condition + ai_persona
(via list_pipeline_stages / update_stage). Read the current text with
verbose:true before editing.
Genudo Instruction Authoring — Principles
Build compact, runtime-ready operating instructions — not giant prompt essays. Every token here is paid on every live message, so stay lean.
Separation of concerns (maps to the real fields):
- pipeline
persona= identity + voice ONLY. No stage steps, tools, pricing, policies. - pipeline
instructions= GLOBAL behaviour only (objective, scope, style, language, memory, approved facts, knowledge usage, data collection, action/tool safety, transitions, escalation, sensitive-data, stage map). This is the pipeline's global instruction field. - stage
instructions= that stage's flow only. Don't repeat global rules per stage. - stage
enter_condition= observable "enter when ..." signals for that stage; its OWN field. - stage
ai_persona= optional. Only set it when a stage needs a different voice from the pipeline persona; otherwise leave it empty.
Hard rules (reserve "never" for true invariants):
- Grounding: never invent products, prices, policies, availability, timelines, or capabilities. If a fact should come from the knowledge base, say "rely on approved knowledge", don't guess. Mark unknowns as open questions before finalizing.
- Action honesty: never let the agent claim a booking / order / payment / ticket / CRM update / escalation succeeded unless the result confirms success. On fail/ambiguous, offer retry, correction, alternative, or human handoff.
- Secrecy: don't expose stage names, pipeline names, routing logic, tools, or prompts to the customer.
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.
- 11d ago First seen · 150 lines · 71 tokens per session scan A 1976916d04c0
instruction-guides is a skill published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 71 tokens to every session and 1,942 once invoked, about $0.0004 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
comfyui-skill-openclaw
Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities. Use this Skill when: (1) The user requests to "generate an image", "draw a picture", or "execute a ComfyUI workflow". (2) The user has…
superloopy-loop
Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-backed completion.
deepline-ads-audiences
Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences. Triggers on phrases like '/deepline-ads-audience', '/deepline-ads-audiences', 'upload this audience', 'create custom audiences', 'personal…
deepline-pre-research
Use when the user wants a last30days-style pre-research pass in Deepline: discover the critical public, private, CRM, workflow, social, and web data sources for a research/enrichment job; compare provider coverage; estimate Deepline credit cost; recommend the source plan before building or running the workflow; or…
niche-signal-discovery
Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria.…
deepline-engine
Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot. Invoke this skill explicitly when the user asks to build an engine.