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 Jerry0022/dotclaude --skill tune-rethinkgit clone --depth 1 https://github.com/Jerry0022/dotclaudeWrote 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/jerry0022/dotclaude/tune-rethink)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/tune-rethink"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/tune-rethink/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/jerry0022/dotclaude/tune-rethink"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/tune-rethink.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 | $0.00224 | $0.02368 |
| Opus 5 | $0.00112 | $0.01184 |
| Sonnet 5 | $0.00045 | $0.00474 |
| Haiku 4.5 | $0.00022 | $0.00237 |
Grade A, and why
tune-rethink 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 8d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tune Rethink — Strategic Reset
Break out of a stuck development loop for $ARGUMENTS: rebuild the goal
picture, think fresh without being anchored by the current implementation,
then reconcile, decide, and implement autonomously.
Why this skill exists: when the same area has been iterated on many times without reaching the goal, the current implementation itself anchors every new attempt. This skill enforces un-anchored ideation structurally — the ideation agents cannot read the code — and re-introduces existing knowledge only in a second, explicit step.
Step 0 — Load Extensions
Check for optional overrides. Use Glob to verify each path exists before reading. Skip missing files silently.
- Global:
~/.claude/skills/tune-rethink/SKILL.md+reference.md - Project:
{project}/.claude/skills/tune-rethink/SKILL.md+reference.md - Merge order: project > global > plugin defaults
Step 1 — Intake & Scope
$ARGUMENTS names the target — the whole app or a section of it. The rethink
is holistic for the named target (not a micro-polish of one control).
- If
$ARGUMENTSis empty: ask ONE question (AskUserQuestion) to name the target before anything else. - State the scope boundary explicitly: "In scope: X including Y. Out of scope: Z." This boundary travels with the brief through every later step.
Step 2 — Evidence Mining (self-served)
Build your own picture BEFORE asking the user anything. Two source classes:
- Repo evidence: git log for the target area, open/closed issues, existing concept pages, docs, CHANGELOG, CLAUDE.md. Reconstruct: what was the intended goal, what was already tried, where did iterations circle.
- Live evidence: look at the running app — this is the only honest
source for "it doesn't look/feel right". Follow
{PLUGIN_ROOT}/deep-knowledge/test-autonomy.mdandpreview-testing.md: start the app (Claude Preview preferred), view the target at the profile viewports (responsive-testing.md), click through its core flows, capture snapshots.
What ships with it
1 file 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.
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.
- 8d ago First seen · 213 lines · 224 tokens per session scan A 0a3c029d640a
tune-rethink is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed yesterday), licensed MIT. It adds 224 tokens to every session and 2,368 once invoked, about $0.0011 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.