edit-pipeline-instructions

edit-pipeline-instructions is a skill for Claude Code, Codex from genudo-ai/genudo_mcp. It costs 87 tokens per session (508 once invoked), scanned A, original, MIT.

A procedure for safely changing the instructions that control a live Genudo agent, including its role, general rules, stages, and stage entry conditions.

In plain words
What is it for?
Use it to load, revise, compare, confirm, publish, and record changes to an existing agent's instructions.
Why use it?
It helps prevent accidental changes to the wrong instruction layer and keeps edits reviewable and reversible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to load, revise, compare, confirm, publish, and record changes to an existing agent's instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/genudo-ai/genudo_mcp/edit-pipeline-instructions
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.

Any agent
npx skills add genudo-ai/genudo_mcp --skill edit-pipeline-instructions
Clone the repo
git clone --depth 1 https://github.com/genudo-ai/genudo_mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for edit-pipeline-instructions

README.md
[![agentmods](https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/edit-pipeline-instructions/github.svg)](https://agentmods.dev/skills/genudo-ai/genudo_mcp/edit-pipeline-instructions)
Your own site
<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/edit-pipeline-instructions"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/edit-pipeline-instructions/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.

agentmods 80×15 button for edit-pipeline-instructions

Your own site · 80×15
<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/edit-pipeline-instructions"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/edit-pipeline-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 508 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00087 $0.00508
Opus 5 $0.00044 $0.00254
Sonnet 5 $0.00017 $0.00102
Haiku 4.5 $0.00009 $0.00051

Measured 11d ago against content hash 6eb2a164f340, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

edit-pipeline-instructions 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.

chatgpt/genudo-chatgpt-plugin/skills/edit-pipeline-instructions/SKILL.md · 37 lines

What it actually says

Edit Pipeline Instructions

Edit a live agent's four instruction fields — pipeline persona, pipeline instructions (global), stage instructions (flow), stage enter_condition (entry) — safely and reversibly.

Run the shipped playbook

Run the editing-playbook skill and follow it exactly; run the instruction-guides skill for the authoring rules. The playbook is the source of truth for the load → mirror → stage → line-edit → diff → confirm → push → record workflow and the local file paths (the pipelines/<slug>/ mirror, its versions/ snapshots, and the staging root). Do not restate or diverge from it.

The layer decision (get this right before editing)

Symptom Field Read via Write via
"who the agent is" / tone pipeline persona list_pipelines update_pipeline
a rule that applies in every stage (product intro, behavioural note) pipeline instructions list_pipelines update_pipeline
the flow inside one stage stage instructions list_pipeline_stages update_stage
when a stage should start stage enter_condition list_pipeline_stages update_stage

Non-negotiables

  • Change only the lines that must change; keep everything else byte-for-byte.
  • Show a before/after diff and the expected business impact.
  • Never call update_pipeline / update_stage without an explicit "yes, push."
  • Pass only the changed fields.
  • After the push returns, record it in the version folder — CHANGES.md **Status:** PUSHED · <timestamp> and manifest.json. A folder that reads the same before and after a push cannot answer "did this ship?", which is the whole point of staging.
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. 11d ago First seen · 37 lines · 87 tokens per session scan A 6eb2a164f340

Subscribe to this mod's changes

edit-pipeline-instructions is a skill published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 87 tokens to every session and 508 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.

Related

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…

HuangYuChuh/ComfyUI_Skills_OpenClaw · 125 tokens

superloopy-loop

Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-backed completion.

beefiker/superloopy · 31 tokens

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…

getaero-io/gtm-eng-skills · 133 tokens

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…

getaero-io/gtm-eng-skills · 135 tokens

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.…

getaero-io/gtm-eng-skills · 135 tokens

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.

getaero-io/gtm-eng-skills · 43 tokens