Kartik-Doye/Ravengard-AI-Recruiter / .agents/skills/handsfree
handsfree
VerifiedGoverns autonomous execution by reversibility, blast radius, external effects, secrets, spend, destructive state, and host-enforced permissions. Use when the user wants fewer interruptions, continued work, or a clear distinction between safe defaults and required approval.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.5 KB |
| references/decision-policy.md | markdown | 2.6 KB |
| references/execution-record.md | markdown | 2.1 KB |
| references/host-permissions.md | markdown | 1.4 KB |
| references/research.md | markdown | 862 B |
references/host-permissions.md
View on GitHub# Host permissions and sandboxes
Hosts may enforce read-only modes, workspace sandboxes, command allowlists,
network restrictions, native approval prompts, or organization policy. These
controls are external authority, not inconveniences for a skill to route around.
## Detect
Use host-provided state when available. If the mode or policy cannot be
observed, call it unknown. Do not infer broad permission from one successful
action.
Recheck official host documentation before naming a current mode, setting, or
configuration path. Those details change faster than this portable skill.
## Operate
- Prefer work that fits the active sandbox.
- Batch related safe reads when that reduces native prompt churn.
- Never combine unrelated risky actions to obtain one broad approval.
- Treat an approval as authority for the exact action and scope shown.
- Preserve the user's dirty state and external resources.
- A denial ends that branch. Continue independent safe work.
## Report
Use precise language:
```text
Blocked by host permission: [action].
Completed independently: [work not dependent on it].
Needs user action: [the smallest host-native approval or configuration step].
```
A skill may explain the host's native approval-memory mechanism once. It must
not edit host security settings, click approval controls on the user's behalf,
or disguise a denied action as another command.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |