coograph: Skill for Claude Code

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

coograph-suggest-multi-models is a skill for Claude Code from paullukic/coograph. It costs 73 tokens per session (1,703 once invoked), scanned A, original, MIT.

A recommendation workflow that suggests which AI model each Coograph agent should use for a project or ticket. It compares the agents' expected work with published model prices and does not apply a change without approval.

In plain words
What is it for?
Use it to review or change per-agent model assignments, estimate the price difference between choices, and restore model selection for a project.
Why use it?
It helps avoid using an expensive model for simple reading tasks or an unsuitable model for difficult reasoning. The choice is based on the work at hand rather than a fixed project-wide setting.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is paullukic/coograph's own configuration. It tells Claude Code 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 →

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-suggest-multi-models/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/paullukic/coograph

Made for: Claude Code.

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-suggest-multi-models

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/paullukic/coograph/coograph-suggest-multi-models"><img src="https://agentmods.dev/badge/skills/paullukic/coograph/coograph-suggest-multi-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,703 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 $0.00073 $0.01703
Opus 5.5 $0.00029 $0.00681
Sonnet 5.5 $0.00015 $0.00341
Haiku 4.5 $0.00007 $0.00170

Measured 1mo ago against content hash 99bbbaa0d678, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coograph-suggest-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-suggest-multi-models/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You propose a per-agent model mapping. You never apply one the user has not accepted, and you never touch the model their own session runs on.

Why This Matters

Coograph delegates to six agents whose demands differ by an order of magnitude. explore reads a great deal and decides little; debugger reads little and decides everything. Running all six on one model either overpays for the reading or underpowers the thinking. The right split depends on the change in front of you, which is why this is a suggestion at a moment you know something about the work, not a table shipped in a template.

The catalogue

Read models.catalog in openspec/config.yaml. It is the project's own: each alias bound to the model id their tool loads, and rough per-million-token rates.

models:
  catalog:
    cheap:   { id: claude-haiku-4-5, in: 1,  out: 5  }
    capable: { id: claude-opus-5,    in: 5,  out: 25 }

Reason about what is in there, never a table you remember. The rates are theirs; say so, and say they are estimates rather than measured spend.

No catalogue declared. Nothing changes: on Claude Code the built-in aliases fable, opus, sonnet, haiku still work exactly as before. On any other tool, say that a catalogue is needed because that tool loads different model ids, show the block above, and stop. Do not invent ids.

An alias in preset with no catalogue entry is an error, not a guess. Name the alias and stop.

Never infer a catalogue. Not from an API key, an installed SDK, an environment variable, or the tool in use. If it is not declared, it does not exist.

Two things to keep saying: a top-tier model usually costs several times the mid one and is for genuinely hard, long-horizon work rather than a default, and a cheap model on a judgment task spends the saving again on the next session.

The starting mapping

Begin from this and adjust for the project or ticket. Reasons matter more than the table; give one per line.

Roles map to catalogue aliases, not to model names. The shape below uses the example aliases; substitute whatever the project declared.

Read the full file on GitHub · 95 lines

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 Changed · +32 lines · -6 tokens per session 99bbbaa0d678
  2. 1mo ago First seen · 63 lines · 79 tokens per session scan A 365992794d29

Subscribe to this mod's changes

coograph-suggest-multi-models is a skill published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It adds 73 tokens to every session and 1,703 once invoked, about $0.0003 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.

Related

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

coograph-suggest-multi-models next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
coograph-suggest-multi-modelspaullukic/coographSkill1712d agoMITA73Claude Code
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