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 agentmods add commands/pealmeida/anymodel-plugin/setupgit clone --depth 1 https://github.com/pealmeida/anymodel-pluginWhat 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 | $0.00015 | $0.00304 |
| Opus 5 | $0.00008 | $0.00152 |
| Sonnet 5 | $0.00003 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" setup --json $ARGUMENTS
If the result says the default engine is unavailable and npm is available:
- Use
AskUserQuestionexactly once to ask whether Claude should install it now. - Put the install option first and suffix it with
(Recommended). - Use these two options:
Install engine (Recommended)Skip for now
- If the user chooses install, follow the engine's documented install procedure (for
codex,npm install -g @openai/codex), then rerun:
node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" setup --json $ARGUMENTS
If the engine is already installed or npm is unavailable:
- Do not ask about installation.
Output rules:
- Present the final setup output to the user.
- If installation was skipped, present the original setup output.
- If the engine is installed but not authenticated, preserve the guidance to run its login command (for
codex,!codex login). - Preserve provider-registry probe results and any review-gate state 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.
- yesterday First seen · 33 lines · 15 tokens per session scan A bfcbde11088e
setup is a command published in the GitHub repository pealmeida/anymodel-plugin (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 15 tokens to every session and 304 once invoked, about $0.0001 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 commands, from other repositories
step-research
Always research before proposing a fix. The Untether bug you're chasing is often a known upstream engine quirk, a previously-fixed regression, or a documented config gotcha.
/release
Release a new version — updates CHANGELOG, pyproject.toml, creates git tag, and pushes.
warden-cost
Dollar accounting — what does each active rule actually save, in money? Translates the token-measured verdict into dollars using a price table and the agent's own token-type mix, with a per-session net and a break-even. Read-only; spends no tokens.
setup-team
Set up River Review in the current project: create .river/rules.md, confirm plugin install, and check integration mode.
checkpoint
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.
weekly-review
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.