Borrowing it
Nothing to install: this file belongs to friedbotstudio/baseline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/friedbotstudio/baseline/main/.claude/skills/claude-automation-recommender/SKILL.mdgit clone --depth 1 https://github.com/friedbotstudio/baselineWrote 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/friedbotstudio/baseline/claude-automation-recommender)<a href="https://agentmods.dev/skills/friedbotstudio/baseline/claude-automation-recommender"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/claude-automation-recommender.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 | $0.00077 | $0.04289 |
| Opus 5 | $0.00039 | $0.02145 |
| Sonnet 5 | $0.00015 | $0.00858 |
| Haiku 4.5 | $0.00008 | $0.00429 |
Grade A, and why
claude-automation-recommender 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 6d 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Automation Recommender
Analyze codebase patterns to recommend tailored Claude Code automations across all extensibility options.
This skill is read-only. It analyzes the codebase and outputs recommendations. It does NOT create or modify any files. Users implement the recommendations themselves or ask Claude separately to help build them.
Working with the baseline
This skill is invoked from inside a project that ships the Claude Code Baseline (
docs/init/seed.md). Read that file before recommending — it lists what is already installed.
The baseline already provides the following. Do not recommend any of these as additions — they exist:
- 22 hooks: 17 write/run-boundary guards —
setup_guard,destructive_cmd_guard,git_commit_guard,env_guard,direction_approval_guard,swarm_approval_guard,verify_pass_guard,track_guard,artifact_template_guard,plantuml_syntax_guard,spec_diagram_presence_guard,spec_design_calls_guard,swarm_boundary_guard,tdd_order_guard,process_lifecycle_guard,lint_runner,test_runner— plus 4 lifecycle hooks:memory_session_start,memory_stop,memory_pre_compact,harness_continuation— plus 1 input-boundary hook:consent_gate_grant. - 1 subagent:
swarm-worker— the only subagent in the baseline. It executes pre-decided recipes from main context inside isolated git worktrees during/swarm-dispatch. No new subagents should be recommended. All decision-making lives in skills running in main context, where conversational nuance and full file visibility are preserved. - 36 skills: artifact drafting (4), workflow phases (10), phase workers —
scenario,implement,verify,prose,design-ui(5), spec helpers —spec-lint,spec-render,spec-diagram-review,spec-traceability-review(4), orchestration —harness,swarm-plan,swarm-dispatch(3), memory —memory-sync(1), audit —audit-baseline(1), alternate tracks —chore(1), plus seven shared globals:claude-automation-recommender,code-structure,humanizer,documentation,technical-tutorials,copywriting,impeccable. Several skills mandatorily invoke another skill:scenarioandimplementinvokecode-structure;design-uiinvokesimpeccable;proseinvokeshumanizer(always) andcopywriting(when persuasive). Thetechnical-tutorialsskill carries its audience-context reference doc inline at.claude/skills/technical-tutorials/references/audience-context.md(consolidated 2026-04-28 from the upstreamdeveloper-audience-contextskill). - 4 commands:
/approve-direction,/approve-swarm,/grant-commit,/init-project. - 3 MCP servers: the documentation provider named in
.claude/docs-provider.json(library docs),plantuml(diagram rendering),playwright(Microsoft-official browser automation; used bydesign-uifor cross-engine visual verification, byintegratefor optional cross-engine smoke).
What ships with it
7 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.
- 6d ago First seen · 365 lines · 77 tokens per session scan A 09892009d6dc
claude-automation-recommender is a skill published in the GitHub repository friedbotstudio/baseline (14 stars, last pushed 3d ago), licensed Apache-2.0. It adds 77 tokens to every session and 4,289 once invoked, about $0.0004 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
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。.
securing-agentic-ai-tool-invocation
Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.
rust-review
Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记.
python-review
Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出.