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 Malo-T/claude-toolbelt --skill ignore-setupgit clone --depth 1 https://github.com/Malo-T/claude-toolbeltWrote 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/malo-t/claude-toolbelt/ignore-setup)<a href="https://agentmods.dev/skills/malo-t/claude-toolbelt/ignore-setup"><img src="https://agentmods.dev/badge/skills/malo-t/claude-toolbelt/ignore-setup/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/malo-t/claude-toolbelt/ignore-setup"><img src="https://agentmods.dev/badge/skills/malo-t/claude-toolbelt/ignore-setup.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 | $0.00157 | $0.01660 |
| Opus 5 | $0.00078 | $0.00830 |
| Sonnet 5 | $0.00031 | $0.00332 |
| Haiku 4.5 | $0.00016 | $0.00166 |
Grade A, and why
ignore-setup 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 11d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ignore Setup
Configure a project so the default file discovery is clean, while every excluded path stays readable on purpose. Three layers, one command.
/clean-context:ignore-setup
Measuring the before/after counts and writing patterns from the catalogue below is mechanical — don't deliberate over it. Save the actual thinking for the guardrails: what counts as generated, and when to ask before excluding something.
.claudeignore does not exist
If that is what was asked for, say so once and move on — it is the most common wrong turn here.
There is no .claudeignore in Claude Code (verified by inspecting the 2.1.x binary: zero
occurrences of claudeignore, CLAUDE_IGNORE, ignoreFile). A file placed at the root does
nothing at all. What exists instead:
| Lever | Read |
Grep |
Glob |
@ picker |
|---|---|---|---|---|
.gitignore / .ignore |
ignores it, reads anyway | respected | not respected | respected |
env: CLAUDE_CODE_GLOB_NO_IGNORE=false |
— | — | makes Glob respect them | — |
permissions.deny: ["Read(…)"] |
hard block, no prompt | excluded | excluded | excluded |
Grep runs ripgrep without --no-ignore (only .git, .svn, .hg, .bzr, .jj, .sl are
excluded in code), so it already obeys ignore files. Glob passes --no-ignore --hidden unless the
env var above says otherwise. Read-deny rules are turned into negative ripgrep globs for Grep,
Glob and the project file listing — that is the only lever that hides and blocks.
The consequence that shapes everything below: an ignore file hides a path from discovery but
never blocks Read. Clean by default, explicit on demand. permissions.deny is a wall, so it
is for secrets only. permissions.ask is not a middle ground — only deny feeds the Grep/Glob
exclusions, so it costs a prompt per read and cleans nothing.
These are version-specific facts (checked on 2.1.222). If a behaviour below does not reproduce, re-check it rather than trusting this table.
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.
- 11d ago First seen · 132 lines · 157 tokens per session scan A a4fe1365c963
ignore-setup is a skill published in the GitHub repository Malo-T/claude-toolbelt (2 stars, last pushed 20d ago), licensed MIT. It adds 157 tokens to every session and 1,660 once invoked, about $0.0008 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
cold-outreach
Research a prospect, evaluate fit, draft a personalized cold email, preview it to yourself, send it via Resend, and track it in a bounded ledger. Use when the user asks to "research a company/prospect", "check out this lead", "draft a cold email", "send cold outreach", "outreach to this business", "deep dive on this…
email-broadcasts
Draft, test, and send marketing / product-update email broadcasts to an audience via Resend. Use when the user asks to "send a broadcast", "email blast", "newsletter", "product update email", "announce something to users", "marketing email", "review request", "how many contacts", "email history", or "what have we…
jina-image-search
Find and scrape images from the web using Jina AI. Use this skill when the user asks to find images, search for photos, get pictures from Unsplash/Pexels/Pixabay, needs stock photos for presentations, websites, or designs, or mentions finding images online.
site-prospector
Find local businesses worth pitching a free demo website to, present them with honest reasoning, let the user pick, then for each: verify the facts, build a site via site-forge, deploy it, and draft tailored multi-channel outreach — logging everything to a bounded ledger. Use whenever the user wants to find prospects…
github-audit
Audit GitHub repo health, auto-fix safe issues, run quality gates, deploy, and record decisions across runs. Use when asked to audit a repo, check repo/CI/dependency health, run pre-deploy quality checks, or ship after an audit.
site-forge
Build a distinctive, production-grade website (single-page or multi-page) — and an optional Remotion promo video — for any business, product, or person, then deploy it free. Use whenever the user wants to build, design, mock up, prototype, or pitch a website, landing page, demo/spec site, or portfolio — for a local…