Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/uipath/skills/install-permissionsgit clone --depth 1 https://github.com/UiPath/skillsWrote 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/commands/uipath/skills/install-permissions)<a href="https://agentmods.dev/commands/uipath/skills/install-permissions"><img src="https://agentmods.dev/badge/commands/uipath/skills/install-permissions.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 | $0.00029 | $0.02511 |
| Opus 5 | $0.00015 | $0.01256 |
| Sonnet 5 | $0.00006 | $0.00502 |
| Haiku 4.5 | $0.00003 | $0.00251 |
Grade B, and why
install-permissions scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Global — `~/.claude/settings.json`** — applies to every project. How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install UiPath permission allowlist
Help the user add a curated allowlist of safe uip subcommands to their Claude Code settings so the agent is not prompted on every command.
Why this command exists. Claude Code plugins cannot ship permission rules declaratively — per the plugins docs, only the agent and subagentStatusLine keys are honored in a plugin-shipped settings.json; any permissions block is silently ignored. Without a user-configured allowlist, every Bash(...) invocation prompts for approval, and a realistic Flow or RPA build runs 25+ distinct uip subcommands.
Steps
-
Ask which variant to install using
AskUserQuestion:- Full — with safety rails (default, recommended) — writes both
allowandask. Cloud-side-effect commands (debug/upload/publish/pack/login) still prompt, even underdefaultMode: bypassPermissionsor--dangerously-skip-permissions. Prevents accidental prod publishes in YOLO mode. - Allow-only — no safety rails — writes only the
allowblock. Power users who explicitly want zero prompts under--dangerously-skip-permissionspick this. Accept that a strayuip solution publishwill execute without confirmation.
- Full — with safety rails (default, recommended) — writes both
-
Ask where to install the allowlist using a second
AskUserQuestion:- Project —
.claude/settings.local.json(default) — applies only to the current project; conventionally not committed to git. - Project —
.claude/settings.json— applies only to the current project; usually committed. - Global —
~/.claude/settings.json— applies to every project. - Just print it — output the JSON only, do not write anything.
- Something else — accept a custom path string.
- Project —
-
Read the target file. If it exists, parse the JSON strictly. If it already contains
permissions.alloworpermissions.ask, preserve existing entries and add only the missing ones (deduplicate by exact string). If there is nopermissionsblock, add one. If the file parses as invalid JSON, abort with a clear message and ask the user to fix it manually — do not attempt to rewrite.
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 · 143 lines · 29 tokens per session scan B b8edbfa9f5ea
install-permissions is a command published in the GitHub repository UiPath/skills (154 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 2,511 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.