ericrisco/rsc-harness / skills/agent-safety
agent-safety
FlaggedUse 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`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.3 KB |
| evals/README.md | markdown | 910 B |
| evals/cases.yaml | config | 3.2 KB |
| references/threat-model.md | markdown | 4.0 KB |
evals/README.md
View on GitHub# Evals: agent-safety
These cases are the trigger contract and capability rubric for the `agent-safety` skill.
`should_trigger` and `should_not_trigger` assert that the description routes correctly —
each negative names the real sibling it should route to instead (building-agents,
security-audit, agent-eval, prompt-engineering, cost-tracking). Run them through the repo's
eval harness if one is wired up, or read them directly as the routing spec when reviewing
the description. The `capability` block is not a pass/fail script: it is a rubric a human or
an LLM-as-judge scores a sample guardrail design against — the design must cover every
`must_include` item (deny-by-default tools, untrusted-content mediation, HITL on
irreversible actions, memory hygiene, runtime caps) and map them to the OWASP Agentic Top
10. This is a process/review skill, so there is no `verify.sh`; rigor lives in this eval.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |