Claude Skills · DevOps & Infrastructure
Agent Safety
ericrisco/rsc-harnessUse when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or RAG (that is `building-agents`).
At a glance
This skill is for DevOps & Infrastructure and helps you secure an agent's tool access, prevent prompt injection attacks on agents, and set cost and runtime limits for agents.
git clone --depth 1 https://github.com/ericrisco/rsc-harness
cp -r rsc-harness/skills/agent-safety ~/.claude/skills/agent-safety
Setup, runtime and requirements describe ericrisco/rsc-harness, the repo this skill ships in.
agent-safetyprompt-injectionleast-privilegegovernanceUntrusted Inputhuman-in-the-loop
Also in ericrisco/rsc-harness
View the repoUse when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CU...
Use when making a web UI conform to WCAG 2.2 Level AA — axe-core or Lighthouse a11y violations, keyboard operability, focus management, ARIA...
Use when running or fixing paid acquisition on Google or Meta — campaign structure (Performance Max, Demand Gen, Search, Advantage+), platfo...
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge,...
Use when a creative goal must become a finished media file: pick and order generative-media models per modality — AI voiceover, image-to-vid...
Use when instrumenting product or web analytics — GA4/PostHog SDK wiring, event taxonomy, funnels, double-counted events, consent gating, PI...
Use when constitution, spec, plan and tasks all exist and you want them cross-read against each other before any code is written — the rsc-s...
Use when building, refactoring, or debugging Angular (v20/21+): standalone components, signals, zoneless change detection, @if/@for/@defer c...
Use when writing a client for someone else's REST or GraphQL API: auth flow choice and token refresh, pagination to exhaustion, retry-with-j...
Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error...
Use when writing one long-form article end to end — answer-first lede, question-shaped headings, plus its on-page surface (title, meta, slug...
Use when building a content-driven or marketing site with Astro 6: static-first pages, islands and partial hydration, content collections, s...
Other DevOps & Infrastructure skills
Generate an interactive bash wizard that walks a human through a manual procedure — third-party setup, a one-off migration, an A→B state tra...
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wan...
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before f...
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only throug...
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-comm...
Create a formal specification for an existing GitHub Actions CI/CD workflow, optimized for AI consumption and workflow maintenance.