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/friedbotstudio/baseline/gitignorenpx skills add friedbotstudio/baseline --skill gitignoregit clone --depth 1 https://github.com/friedbotstudio/baselineWhat 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 | $0.00105 | $0.00728 |
| Opus 5 | $0.00053 | $0.00364 |
| Sonnet 5 | $0.00021 | $0.00146 |
| Haiku 4.5 | $0.00011 | $0.00073 |
Grade A, and why
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 2d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gitignore — generate and repair .gitignore
This skill produces a correct .gitignore for the current project. It runs in main context (Article II). It never blocks a commit — enforcement is the gitignore_leak_guard hook's job; this skill repairs what the guard flags.
Source of truth
The canonical baseline must-ignore set lives at .claude/skills/gitignore/baseline-ignores.json (entries spanning secret, state, and tooling categories). Consumer-specific additions live in project.json → gitignore.extra_must_ignore. The same set is read by the install/init merge and by the gitignore_leak_guard hook, so the three never drift.
Steps
- Read the baseline set from
baseline-ignores.jsonand the consumer extras fromproject.json → gitignore.extra_must_ignore. These are mandatory — they MUST end up in the final.gitignore. - Optional enrichment via gitignore.io (network). When the user names stacks (or you infer them from the repo), fetch language/IDE coverage from the gitignore.io service hosted at Toptal:
- List available types:
GET https://www.toptal.com/developers/gitignore/api/list - Generate for a comma-separated list:
GET https://www.toptal.com/developers/gitignore/api/<type1,type2,...>(e.g.node,macos,visualstudiocode) → plain-text.gitignorebody. Use WebFetch. This is enrichment only.
- List available types:
- Offline fallback. If the network is unreachable or the service errors, skip enrichment and write the baseline set only, then tell the user the enrichment was skipped (offline fallback). The baseline correctness never depends on the network — the fallback path is the safety net, not an error.
- Merge add-only. If a
.gitignorealready exists, never overwrite or reorder it. Append only the lines (baseline + enrichment) that are not already present, preserving the existing content byte-for-byte. If none exists, create it from the baseline (+ enrichment). - Confirm. Report which sources contributed (baseline always; gitignore.io types if reached; consumer extras) and whether the offline fallback was used.
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.
- 2d ago First seen · 33 lines · 0 tokens per session scan A 548ba6e1ec1b
gitignore is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 105 tokens to every session and 728 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
dev-standards
Enforces development workflows, quality gates, coding standards, and release processes for the deterministic-agent-control-protocol project. Use when implementing features, fixing bugs, refactoring architecture, adding integrations, updating policies, writing tests, updating documentation, or preparing releases.
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
国际化完整性检查。检查翻译 key 是否缺失、硬编码文本、locale 文件一致性。.
vue-best-practices
Vue 2/3 代码规范检查。包括组件命名、Props 校验、Composition API 规范等。.
python-review
Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出.
rust-review
Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记.