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 agentmods add skills/outlinedriven/odin-gemini-cli-extension/setup-gitignorenpx skills add OutlineDriven/odin-gemini-cli-extension --skill setup-gitignoregit clone --depth 1 https://github.com/OutlineDriven/odin-gemini-cli-extensionWrote 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/outlinedriven/odin-gemini-cli-extension/setup-gitignore)<a href="https://agentmods.dev/skills/outlinedriven/odin-gemini-cli-extension/setup-gitignore"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-gemini-cli-extension/setup-gitignore.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.00760 |
| Opus 5 | $0.00032 | $0.00380 |
| Sonnet 5 | $0.00013 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
setup-gitignore 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.
This is a copy
100% identical to setup-gitignore — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize or idempotently revise the current repo's .gitignore — never the global excludesfile.
Scope
Per-repo only. Never read or write ~/.gitignore, ~/.config/git/ignore, or run git config --global. The user's global excludesfile handles cross-machine noise; this skill handles language/tool specifics for the current repo.
Sources composed (in order)
- gitignore.io — templates keyed by detected language/framework (requires network)
- AI tooling — bundled patterns from
references/AI-TOOLING.md - IDE / editor — bundled patterns from
references/IDE-EDITOR.md - Empirical — untracked paths from
git status, confirmed interactively
Workflow
1. Detect repo root
git rev-parse --show-toplevel
Abort with a clear error if not inside a git repo.
2. Detect languages
Read references/LANGUAGE-DETECTION.md for the manifest → gitignore.io key table. Scan manifests:
fd --max-depth 2 -t f
Match filenames against the detection table; build a comma-separated key list (e.g., rust,node,typescript). If no manifests detected, use an empty key list (bundled blocks still apply).
3. Snapshot existing .gitignore
If .gitignore exists, snapshot it before any modification:
cp .gitignore /tmp/gitignore-snapshot-$(date +%s).bak
4. Surface empirical noise
git status -s -uall | rg '^\?\?' | rg -v '^\?\? \.gitignore'
Cluster untracked paths by top-level directory or extension. Present clusters to the user and wait for explicit confirmation. Do not add any empirical pattern without confirmation.
5. Compose
Run scripts/compose-gitignore.sh <csv> to fetch and merge gitignore.io templates. If the network call fails, tell the user and ask whether to continue with bundled-only mode.
Append the bundled blocks after the API output in order:
# === AI TOOLING ===
<contents of references/AI-TOOLING.md>
# === IDE / EDITOR ===
<contents of references/IDE-EDITOR.md>
# === EMPIRICAL ===
<user-confirmed patterns, one per line>
What ships with it
4 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.
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 First seen · 88 lines · 64 tokens per session scan A f52a64215f22
setup-gitignore is a skill published in the GitHub repository OutlineDriven/odin-gemini-cli-extension (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 760 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to setup-gitignore, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
askme
Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…
git-branchless
Enforce idiomatic git-branchless during planning and executing tasks — detached-HEAD-first work, in-memory rebase via git move, event-log recovery via git undo, deferred branch creation, speculative-merge git sync for base updates. Use when planning or executing multi-commit work, history rewrites, stack edits…
grill-me
Adversarial relentless interview against any plan or design until shared understanding is reached. Walk the decision tree, resolve dependencies one answer at a time, recommend a default per question. Trigger when the user says "grill me", "stress-test this", "interview me about this design", or otherwise asks for…
proof-driven
Proof-driven development. Use when implementing with formal verification using property-based testing, theorem proving, or proof tactics; zero unproven property policy enforced.