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/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/friedbotstudio/baseline/claude-automation-recommender"><img src="https://agentmods.dev/badge/skills/friedbotstudio/baseline/claude-automation-recommender.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 98 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- high Excessive Agency · line 348 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 351 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium MCP Rug Pull · line 64 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Agent Snooping · line 176 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 5.5 | $0.00031 | $0.01716 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 13d ago), licensed Apache-2.0. It adds 77 tokens to every session and 4,289 once invoked, about $0.0003 per session on Opus 5.5. 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
An internationalization (i18n) check for software that supports multiple languages. It compares translation files with the text and translation keys used by the code.
vue-best-practices
A review checklist for Vue 2 and Vue 3 components, covering component names, prop declarations, TypeScript casts, API styles and complex template expressions.
gdpr-audit
GDPR compliance audit of code, plans, schemas, or IaC. Produces a findings report with article citations, severity, confidence, and fixes; flags evidence gaps. Not a substitute for a DPO/lawyer.
cognitive-walkthrough
Deep-dive usability evaluation of specific user tasks. Simulates novice user cognition step-by-step to identify learnability issues, unclear actions, and points of confusion.
owasp-ai-testing
AI trustworthiness testing using OWASP AI Testing Guide v1. Execute 32 test cases across 4 layers (Application, Model, Infrastructure, Data) with practical payloads and remediation.