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 oalders/kitchen-sink --skill tune-preciousgit clone --depth 1 https://github.com/oalders/kitchen-sinkWrote 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/oalders/kitchen-sink/tune-precious)<a href="https://agentmods.dev/skills/oalders/kitchen-sink/tune-precious"><img src="https://agentmods.dev/badge/skills/oalders/kitchen-sink/tune-precious/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.
<a href="https://agentmods.dev/skills/oalders/kitchen-sink/tune-precious"><img src="https://agentmods.dev/badge/skills/oalders/kitchen-sink/tune-precious.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00124 | $0.15773 |
| Opus 5 | $0.00062 | $0.07886 |
| Sonnet 5 | $0.00025 | $0.03155 |
| Haiku 4.5 | $0.00012 | $0.01577 |
Grade B, and why
tune-precious scanned grade B 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 10d 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 deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
After editing `dist.ini`, re-run `dzil build --no-tgz` and confirm `precious.toml` is absent from the build output (`find <DistName>-*/ -name precious.toml` returns nothing). Then revert regenerated build artefacts the w Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 778 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tune Precious
Overview
Six idempotent transforms that land precious as the canonical tidy/lint driver for a Perl repo (or any repo that has opted into typos):
- Generate or refresh
precious.tomlwithperltidy,perlvars,omegasort-gitignore,omegasort-stopwords, optionallyperlcritic, and optionallytypos. - Consolidate the
perltidyprofile to the hidden.perltidyrcand strip-b(precious manages backup mode). - Delete
Code::TidyAllconfig (.tidyallrc,tidyall.ini,.tidyall.d/ignore line). - Edit
dist.inito remove the tidyall plugin + prereqs via the bundle'sPluginRemoverand a trailing[RemovePrereqs]block. - Add a
.github/workflows/lint.ymljob that installsprecious+omegasort(+typoswhen wired) via ubi and runsprecious lint— incrementally (--git-diff-fromthe PR base) onpull_requestevents,--allon every other event. - Add a self-installing
scripts/pre-commitshell hook that runsprecious lint --stagedand blocks direct commits to the default branch, so contributors catch tidy/lint drift before pushing.
Core principle: apply the canonical recipe without changing the user's tidy/lint intent. Each transform is its own commit so any single change is revertable. Re-running on an already-tuned repo is a no-op.
Four modes the skill handles transparently:
| Mode | Trigger | What changes |
|---|---|---|
| Migrate | Repo has .tidyallrc, tidyall.ini, or [Test::TidyAll] in dist.ini |
All six transforms apply |
| Greenfield | Perl repo, no tidyall config, no precious.toml |
T1 + T2 (consolidate any visible perltidyrc) + T5 + T6 |
| Tune | precious.toml already exists |
All transforms run as no-ops; surfaces drift between current config and canonical recipe |
| Typos-only | No Perl files, but typos.toml / _typos.toml / .typos.toml is present |
T1 (typos block only) + T5; T2/T3/T4 are no-ops |
Worked example PR: libwww-perl/WWW-Mechanize-Cached#35 — the recipe was extracted from this PR.
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.
- 10d ago First seen · 778 lines · 124 tokens per session scan B 5a481078f9fe
tune-precious is a skill published in the GitHub repository oalders/kitchen-sink (4 stars, last pushed 10d ago), licensed MIT. It adds 124 tokens to every session and 15,773 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…