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 richfrem/agent-plugins-skills --skill update-cli-modelsgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/update-cli-models)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/update-cli-models"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/update-cli-models.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.01737 |
| Opus 5 | $0.00056 | $0.00869 |
| Sonnet 5 | $0.00022 | $0.00347 |
| Haiku 4.5 | $0.00011 | $0.00174 |
Grade A, and why
update-cli-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 3d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
update-cli-models: Model Catalog Update Protocol
When triggered, execute all steps below in order. This is an active update run — not a reference. Fetch live data, diff against current JSON files, write changes, and sync at the end.
Reference Files (master copies — only these are ever edited directly)
| File | CLI | Key field |
|---|---|---|
plugins/cli-agents/references/copilot-models.json |
copilot |
cli_id uses dot notation e.g. claude-sonnet-4.6 |
plugins/cli-agents/references/agy-models.json |
agy |
Gemini models with thinking levels |
plugins/cli-agents/references/claude-models.json |
claude |
cli_id uses dash notation e.g. claude-sonnet-5 — more models than Copilot |
plugins/cli-agents/references/codex-models.json |
codex |
OpenAI models via codex CLI |
plugins/cli-agents/references/cheapest_models.json |
all | Master cheapest pick per backend |
plugins/cli-agents/references/cheapest_models.md |
all | Master human-readable cheapest + Copilot tier table |
Copies under individual skills are never edited directly — the sync script handles them.
Step 1 — Fetch current data from official sources
Fetch each source using read_url_content. Use the markdown API endpoints
where available — do NOT scrape raw HTML.
| CLI | Fetch URL |
|---|---|
copilot pricing |
https://docs.github.com/api/article/body?pathname=/en/copilot/reference/copilot-billing/models-and-pricing |
copilot model IDs |
https://docs.github.com/api/article/body?pathname=/en/copilot/reference/ai-models/supported-models |
agy (Gemini) |
https://ai.google.dev/pricing |
claude |
https://platform.claude.com/docs/en/about-claude/models/overview |
codex (OpenAI) |
Try https://openai.com/api/pricing/ — if 403, use search_web for "OpenAI API pricing [current year] per million tokens" |
For each source extract:
- Exact CLI identifier (not display name)
- Input / output price per 1M tokens
- Cached input price
- Cache write cost (Anthropic only)
- Context window (if available)
- Long context pricing tiers and thresholds
- Status: GA / preview / withdrawn / deprecated
What ships with it
9 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.
- evals/evals.json 1.0 KB
- references/acceptance-criteria.md 42 B
- references/agy-models.json 35 B
- references/cheapest_models.json 40 B
- references/cheapest_models.md 38 B
- references/claude-models.json 38 B
- references/codex-models.json 37 B
- references/copilot-models.json 39 B
- scripts/sync_cheapest_models.py 40 B runs code
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.
- 3d ago First seen · 147 lines · 111 tokens per session scan A c2a3cdc7caf4
update-cli-models is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 1,737 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
swarm-scripts
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, dbquery, and exposing a script as an API.
todos
Handle the agent personal todos.md file.
mcp-builder
Scaffolds and ships MCP servers in Python (FastMCP) or TypeScript (@modelcontextprotocol/sdk) — tools designed around workflows rather than raw endpoints, with model-guiding schemas and error messages, pagination, a direct-call test harness, and wiring into .mcp.json or claude mcp add. Use when the user says "build an…
Prompt Version Control Workflow
Sets up a prompt versioning system with naming conventions, diff tracking, A/B evaluation gates before promotion, and rollback triggers.
slip
Send AI-written text to a HUMAN outside this chat via a one-tap Slip note and reply with a single URL. Default: toss — a one-shot note (Markdown rendered, readable on open, tear-to-delete, auto-expires in 24 hours) for one-way delivery like checklists, summaries, code snippets. Use push only when the human is expected…
situate-what
Use when the user asks what is going on and needs a five-line summary of the session, branch, pull request, and ticket.