agentmods.dev

coograph: Skill for Claude Code

.github/skills/coograph-disable-multi-models/SKILL.md

coograph-disable-multi-models is a skill for Claude Code, Codex from paullukic/coograph. It costs 56 tokens per session (416 once invoked), scanned A, original, MIT.

A project setting change that turns off per-task AI model selection for Coograph. Afterward, every agent uses the model of the current session and the project stops suggesting model assignments.

In plain words
What is it for?
Use it when a project should use one session model for all agents or when per-task model suggestions are no longer wanted.
Why use it?
It removes unwanted model recommendations and makes model use consistent across agents. The setting can be changed back later with the model-suggestion workflow.

Skill for Claude CodeCodex

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

This is paullukic/coograph's own configuration. It tells Claude Code and Codex how to work on coograph itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything coograph configures →

not rated 17repo 12d ago A scan 56 tokens original MIT
View source ↗ paullukic/coograph coograph.com
Reuse

Borrowing it

Nothing to install: this file belongs to paullukic/coograph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/paullukic/coograph/main/.github/skills/coograph-disable-multi-models/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/paullukic/coograph

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 coograph-disable-multi-models

README.md
[![agentmods](https://agentmods.dev/badge/skills/paullukic/coograph/coograph-disable-multi-models/github.svg)](https://agentmods.dev/skills/paullukic/coograph/coograph-disable-multi-models)
Your own site
<a href="https://agentmods.dev/skills/paullukic/coograph/coograph-disable-multi-models"><img src="https://agentmods.dev/badge/skills/paullukic/coograph/coograph-disable-multi-models/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 coograph-disable-multi-models

Your own site · 80×15
<a href="https://agentmods.dev/skills/paullukic/coograph/coograph-disable-multi-models"><img src="https://agentmods.dev/badge/skills/paullukic/coograph/coograph-disable-multi-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 416 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 $0.00056 $0.00416
Opus 5.5 $0.00022 $0.00166
Sonnet 5.5 $0.00011 $0.00083
Haiku 4.5 $0.00006 $0.00042

Measured 1mo ago against content hash e2412df95855, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coograph-disable-multi-models 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.

.github/skills/coograph-disable-multi-models/SKILL.md · 35 lines

What it actually says

You turn model selection off for this project. One step, no questions.

Why This Matters

An opt-in feature that cannot be declined cleanly is not opt-in. A user who does not want their agents split across models should be able to say so once and never hear about it again, and the answer has to survive a template sync.

Steps

  1. Set models.mode: off in openspec/config.yaml, creating the models block if it is absent. Leave any saved preset in place; it is harmless and means re-enabling does not start from nothing.
  2. Confirm in one line, naming the file.

That is the whole procedure. Do not ask for confirmation first: the user invoked a command whose only job is this.

What off means

  • No skill passes a model override. Every agent inherits the session model, exactly as a project that never opted in.
  • No flow suggests a mapping. coograph-new-ticket and coograph-plan do not ask.
  • The one-line model footer at the end of a delegated run still appears, naming the inherited model. It is the surface that tells a user their setting is being honoured, so it stays in every mode.
  • /coograph-suggest-multi-models is the way back. Running it re-enables the project.

Guardrails

  • Never delete the preset map. Turning off is not the same as forgetting.
  • Never touch anything else in openspec/config.yaml; that file holds the user's project context and rules.
  • Never change the model the user's own session runs on.
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. 1mo ago First seen · 35 lines · 56 tokens per session scan A e2412df95855

Subscribe to this mod's changes

coograph-disable-multi-models is a skill published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It adds 56 tokens to every session and 416 once invoked, about $0.0002 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 2026-09-21.

Building agentsai-agentsai-codingai-optimizationai-toolscode-graphtoken-ai-optimizator
Related

coograph-disable-multi-models compared with skills from other repositories

coograph-disable-multi-models next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
coograph-disable-multi-modelspaullukic/coographSkill1712d agoMITA56Claude Code, Codex
managing-mcp-serversJetBrains/thinkrailSkill7.8kyesterdayApache-2.0A62Claude Code, Codex
todosJetBrains/thinkrailSkill7.8kyesterdayApache-2.0A58Claude Code, Codex
writing-workflow-skillsJetBrains/thinkrailSkill7.8kyesterdayApache-2.0A60Claude Code, Codex
ai-ml-developmenttravisjneuman/.claudeSkill107yesterdayMITA43Claude Code, Codex
performance-engineeringtravisjneuman/.claudeSkill107yesterdayMITA38Claude Code, Codex
case-interview-practicetravisjneuman/.claudeSkill107yesterdayMITA39Claude Code, Codex