A command that runs a local process-skill optimizer, which improves the written procedure an agent follows for a task. It can either print a command for a separate terminal or run the process in the current session.

Use it to optimize a named process skill, inspect its fixtures, or run the optimizer after creating a clean Git checkpoint.

It provides a safer default for a process that can make destructive file or repository changes when run with broad permissions.

skillopt — Command for Claude Code by iliaal/whetstone

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/iliaal/whetstone

agentmods

npx agentmods add commands/iliaal/whetstone/skillopt

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/iliaal/whetstone/skillopt/github.svg)](https://agentmods.dev/commands/iliaal/whetstone/skillopt)

Your own site

<a href="https://agentmods.dev/commands/iliaal/whetstone/skillopt"><img src="https://agentmods.dev/badge/commands/iliaal/whetstone/skillopt/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/iliaal/whetstone/skillopt"><img src="https://agentmods.dev/badge/commands/iliaal/whetstone/skillopt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,599 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.01599
Opus 5.5	$0.00016	$0.00640
Sonnet 5.5	$0.00008	$0.00320
Haiku 4.5	$0.00004	$0.00160

Measured 1mo ago against content hash b3a3864440fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

skillopt scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

hazard that has let a target agent `rm -rf` fixtures and `git commit` in the host

.claude/commands/skillopt.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/skillopt — run the SkillOpt process-skill optimizer

Optimize a Whetstone process skill via distillery/skillopt/. Full procedure and rationale: distillery/skillopt/SKILLOPT-RUNBOOK.md.

Safety — read before `--run`

The optimizer drives a bypassPermissions target agent with its bash sandbox disabled. Running it nested inside a Claude Code session is the documented hazard that has let a target agent rm -rf fixtures and git commit in the host repo (see the Safety section of distillery/skillopt/SKILLOPT-RUNBOOK.md). Therefore:

Default mode does NOT run the agent in-session — it validates + prints the exact command to run in a bare terminal.
--run executes in-session only after the rollout's _ensure_unsandboxed unsets CLAUDE_CODE_COORDINATOR_MODE (confines each nested agent's Bash root to its out-of-repo tmpdir) AND a clean git checkpoint exists. Relative-path escape is closed by design; absolute-path access still is not — use --run only on your own curated fixtures, and prefer the default.

Arguments

skill (default ia-debugging) — the process skill to optimize.
--fixtures <dir> (advanced) — override the fixture set named in the skill's config; defaults to whatever configs/whetstone/<skill>.yaml points at.
--target <model> (default: the config's weak target) — override the weak target to optimize for; capable models saturate hard, leaving no room.
--weight <λ> (default auto) — soft blend weight; must be < 1/n_val.
--epochs N (default 2).
--run — execute in-session (hardened) instead of printing the command.

Procedure (follow exactly)

Resolve the per-skill config. CONFIG = distillery/skillopt/configs/whetstone/<skill>.yaml. If it does not exist, the skill is not onboarded — SkillOpt needs four pieces per skill: fixtures, a RUBRICS[<skill>] entry in skillopt/envs/whetstone/rubric.py, this config, and a seed (env.skill_init). Tell the user to onboard it (see the runbook §5) and STOP. Do not fall back to default.yaml — that silently optimizes ia-debugging's skill against the wrong fixtures. Read FIXDIR from the config's env.tasks_root (a tasks/ dir) and set SETDIR to its parent — the fixture-set root, where build_fixtures.py and splits/ live (not inside tasks/). Confirm FIXDIR, the sibling splits/{train,val,test}/items.json, and $SETDIR/build_fixtures.py exist.

Read the full file on GitHub · 99 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.

1mo ago Changed b3a3864440fa
1mo ago First seen · 99 lines · 40 tokens per session scan C 85244f295d5a

Subscribe to this mod's changes

skillopt is a command published in the GitHub repository iliaal/whetstone (35 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 1,599 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Claude Code Code review agent-skills ai-agents ai-tools claude-code-plugin

sm-buff

You usually don't run buff directly — run sm sail. sm sail drives the whole PR to green and calls buff watch / triage for you, stopping only when it needs you to act (see /sm-sail). Reach for sm buff here only for surgical work: inspecting a specific failure, or resolving a single review thread when sail has parked on…

ScienceIsNeato/slop-mop · 0 tokens

skillopt

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Recursive force deletehighDestructive command

How it starts

/skillopt — run the SkillOpt process-skill optimizer

Safety — read before `--run`

Arguments

Procedure (follow exactly)

What this file has done since we first saw it

Other commands, from other repositories

sm-buff

sm-scour

review

speckit.boundedrelay.plan-review

speckit.boundedrelay.implementation-review

open-pr

skillopt

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Recursive force deletehighDestructive command

How it starts

/skillopt — run the SkillOpt process-skill optimizer

Safety — read before --run

Arguments

Procedure (follow exactly)

What this file has done since we first saw it

Other commands, from other repositories

sm-buff

sm-scour

review

speckit.boundedrelay.plan-review

speckit.boundedrelay.implementation-review

open-pr

Safety — read before `--run`