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 brooksbUWO/tweakcc-gilligan --skill tweakcc-updategit clone --depth 1 https://github.com/brooksbUWO/tweakcc-gilliganWrote 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/brooksbuwo/tweakcc-gilligan/tweakcc-update)<a href="https://agentmods.dev/skills/brooksbuwo/tweakcc-gilligan/tweakcc-update"><img src="https://agentmods.dev/badge/skills/brooksbuwo/tweakcc-gilligan/tweakcc-update/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/brooksbuwo/tweakcc-gilligan/tweakcc-update"><img src="https://agentmods.dev/badge/skills/brooksbuwo/tweakcc-gilligan/tweakcc-update.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 | $0.00126 | $0.05258 |
| Opus 5 | $0.00063 | $0.02629 |
| Sonnet 5 | $0.00025 | $0.01052 |
| Haiku 4.5 | $0.00013 | $0.00526 |
Grade A, and why
tweakcc-update 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 5d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tweakcc-gilligan: Dual-Patcher Skill for Claude Code
tweakcc-gilligan customizes the user's own locally installed Claude Code binary on Windows, Linux, and macOS in two stages. It applies tweakcc-fixed (code patches, /clear-screen, session memory, empty system-reminder suppression) and unnerfcc (rewrites of the prompt text strings shipped inside the product binary; raises the default reasoning-effort configuration). It also fills system-reminder overrides from lobotomized-claude-code. Everything here operates on plain text strings shipped in the installed product on the user's machine; nothing reads, extracts, or infers model internals.
Portability warning: allowed-tools is enforced by the Claude Code CLI only.
Agent SDKs ignore it. If you load this skill via the Python or TypeScript SDK,
replicate these restrictions in ClaudeAgentOptions (Python) or Options
(TypeScript), or the skill will run with unrestricted tools.
Core rules (read first)
| # | Rule |
|---|---|
| 1 | Run --prepare before --apply. --apply does not build; it needs the dist that --prepare produces. A bare --apply on a fresh clone dies with "dist/index.mjs missing". |
| 2 | The apply runs OUTSIDE Claude Code with ALL sessions closed. A running claude.exe locks the binary. |
| 3 | The extractor commit must match the target binary format (see references/version-update.md, binary-format section). Wrong format = "claude module not found in any of the binary modules" (tweakcc-fixed) or "BUN_FORMAT_INCOMPATIBLE / struct-size ambiguity" (unnerfcc). |
| 4 | One clone per repo. Never create a second copy, snapshot, branch-named dir, or zip of a repo. Duplicates are the top failure source: edits land in one copy, get committed from another, and drift. |
| 5 | Never hand-edit the runtime clones in ~/.tweakcc-gilligan/repos/. They are disposable; --prepare rebuilds them. Edit and commit source only in its one dev location, then let the installer clone fresh from the remote. |
| 6 | Do not use git worktrees. Work in the main checkout. |
| 7 | A new CC version is a MECHANICAL re-patch (references/version-update.md): the rewrites are already decided and encoded as rules; only stock anchors move. Changing un-nerf CONTENT is a separate job (the "Remediation" section): recipe-driven, run through the GSD phases with gsd-verifier gating each one; never force past a failed gate. Never mix the two jobs: mixing them is how a 1-hour patch became a 9-day milestone. |
| 8 | This skill lives in two locations that must stay byte-identical: the DEV source tweakcc-gilligan/skills/tweakcc-update/ and the INSTALLED copy .claude/skills/tweakcc-update/. After any edit, copy to the other side and run python scripts/test_skill_mirror_sync.py (exit 0). |
What ships with it
13 files 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.
- references/concept-map-dispatch-prompt.md 8.8 KB
- references/gates.md 2.9 KB
- references/pipeline.md 6.4 KB
- references/version-update.md 15 KB
- scripts/check_encode_coverage.py 7.9 KB runs code
- scripts/check_version_intersection.py 12 KB runs code
- scripts/install.py 47 KB runs code
- scripts/test_check_encode_coverage.py 1.5 KB runs code
- scripts/test_classify_patcher_output.py 1.2 KB runs code
- scripts/test_select_tweakcc_ref.py 3.9 KB runs code
- scripts/test_skill_mirror_sync.py 4.1 KB runs code
- scripts/test_termination_contract.py 8.4 KB runs code
- scripts/verify.py 9.1 KB runs code
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.
- 5d ago Changed · +74 lines db7f94acfe99
- 10d ago First seen · 182 lines · 126 tokens per session scan A ed994e63cf9b
tweakcc-update is a skill published in the GitHub repository brooksbUWO/tweakcc-gilligan (2 stars, last pushed 6d ago), licensed MIT. It adds 126 tokens to every session and 5,258 once invoked, about $0.0006 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
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…