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 skills/thgmatajs/squirrel-mode/tunenpx skills add thgMatajs/squirrel-mode --skill tunegit clone --depth 1 https://github.com/thgMatajs/squirrel-modeWrote 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/thgmatajs/squirrel-mode/tune)<a href="https://agentmods.dev/skills/thgmatajs/squirrel-mode/tune"><img src="https://agentmods.dev/badge/skills/thgmatajs/squirrel-mode/tune.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 | $0.00026 | $0.00866 |
| Opus 5 | $0.00013 | $0.00433 |
| Sonnet 5 | $0.00005 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
tune 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
squirrel-mode tuning
/squirrel:tune edits one field of the existing profile at ~/.squirrel/profile.md. It never re-runs the seven-question interview.
Procedure
- Read
~/.squirrel/profile.md. If it does not exist, say so in one line, tell the user to run/squirrel:initfirst, and stop there. - Show the current value of all 11 fields as one compact block:
language,answer_position,step_style,max_list_items,code_style,explanation_budget,options_per_answer,confirm_topic_switch,progress_recap,extras_section,tone. If the file exists but a given field's line is missing entirely, or is malformed - not in the exactfield: valueshape, or carrying a value outside that field's allowed values - show that field as unset (for example,tone: (unset)) rather than guessing a value, and treat it as therules/base-rules.mddefault for that field until the user sets it explicitly through this command. Do not write that default into the file on your own initiative; showing it is not setting it. - Ask exactly one question: which field to change, and to what. Offer field-name options as multiple-choice when 4 or fewer are the likely candidates from context; otherwise ask the user to name the field directly.
- Any of the 11 fields can be changed this way, one at a time, including the four that
/squirrel:initquestion 2 set together as a bundle (step_style,explanation_budget,extras_section,tone). Each of the four is independently editable here even though the interview only ever set it alongside the other three. - Validate the new value against the allowed values for that field before writing anything:
language:pt-BR,en,es, orauto.answer_position:firstorafter-one-line-context.step_style:numberedorchecklist.max_list_items: an integer from 3 to 7.code_style:code-firstorstep-by-step.explanation_budget: a positive integer.options_per_answer: a positive integer.confirm_topic_switch:yesorno.progress_recap:yesorno.extras_section:yesorno.tone:neutral,warm, orterse. If the requested value is not on this list, say so in one line and ask again, for that same field only.
- Rewrite
~/.squirrel/profile.mdwith the new value in place and every other field unchanged, keeping the samefield: valueshape the file already has. Write is non-atomic (ADR-0003 Amendment P3); other open Claude Code sessions pick up the change on their next prompt via profile mtime reinjection - do not invent an installer-style write script. - Confirm the change in one line, naming the field and its new value. Do not re-show the whole profile unless asked.
- If the user asks to change more than one field, handle them one at a time: confirm the first change, then repeat the one-question step for the next field. Never ask about two fields in the same message.
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 · 40 lines · 26 tokens per session scan A 62ffde3ba586
tune is a skill published in the GitHub repository thgMatajs/squirrel-mode (2 stars, last pushed 15d ago), licensed MIT. It adds 26 tokens to every session and 866 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 skills, from other repositories
hyperfocus
ADHD-friendly output formatting. Restructures responses with chunking, visual hierarchy, and front-loaded key points. Modes: clean, flow (default), zen. Use when user says "hyperfocus", "focus mode", "adhd mode", "adhd friendly", or invokes /hyperfocus.
glossary-init
USE WHEN setting up a repo for AI-first work, when an agent hallucinates domain term meaning, or when user asks to bootstrap / extend the repo's domain glossary. Surfaces candidate terms by identifier frequency, asks the user for 1-sentence definitions, writes GLOSSARY.md at repo root. Idempotent — re-running adds new…
codex-pair-resume
Resume codex-pair for this project after a previous pause. Removes .codex-pair/state/paused and clears failure state. Review resumes on the next supported file edit; missing state is a no-op.
conventions-init
USE WHEN setting up a repo for AI-first work (after /init-repo), or when the context-surface hook should start feeding repo conventions to agents before edits. Drafts conventions.yml at repo root: per-kind casing (inferred from the code), a vague-name denylist seed, directory roles, and a hand-filled house-rules…
opik
This skill should be used when the user needs to add Opik tracing or integrations to their code, instrument an LLM application, or needs reference for Opik SDK usage (Python, TypeScript, REST API). Use for tasks like "add tracing", "instrument my code", "use trackopenai", "add OpikTracer", "what span types are…
codex-review
Get a second opinion from OpenAI Codex on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. Use when user asks to "review with Codex", "Codex code review", or "ask Codex to check my code".