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 skills add marcelocruzrpa/uipath-ai-skills --skill uipath-tasksgit clone --depth 1 https://github.com/marcelocruzrpa/uipath-ai-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/skills/marcelocruzrpa/uipath-ai-skills/uipath-tasks)<a href="https://agentmods.dev/skills/marcelocruzrpa/uipath-ai-skills/uipath-tasks"><img src="https://agentmods.dev/badge/skills/marcelocruzrpa/uipath-ai-skills/uipath-tasks/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/marcelocruzrpa/uipath-ai-skills/uipath-tasks"><img src="https://agentmods.dev/badge/skills/marcelocruzrpa/uipath-ai-skills/uipath-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.02970 |
| Opus 5.5 | $0.00055 | $0.01188 |
| Sonnet 5.5 | $0.00028 | $0.00594 |
| Haiku 4.5 | $0.00014 | $0.00297 |
Grade A, and why
uipath-tasks 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 2mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UiPath Tasks Skill
Generate Tasks workflows for human-in-the-loop, system-in-the-loop, and task management patterns in UiPath.
Plugin architecture: This skill's
extensions/directory is auto-discovered by uipath-core'splugin_loader.py. Generators, lint rules, scaffold hooks, namespaces, and known activities are registered at import time — no manual wiring needed. Core'sgenerate_workflow.py,validate_xaml, andscaffold_project.pyquery the plugin registries at runtime.
Plugin API contract (v2)
This skill is the canonical example for out-of-tree plugin authors. The contract:
REQUIRED_API_VERSION = 2must be declared at the top ofextensions/__init__.py. Plugins on v1 (or with no declaration) fail to load with a clearAPI version mismatcherror and any partial registrations are rolled back.- Registration entry points added in v2:
register_version_profile(package, profile_version, profile_dict)andregister_band_profile_mapping(band, package, profile_version)— used by lint 122 (version-band drift). Callregister_band_profile_mappingonce per(band, package)pair. Registering after the lint module is already imported automatically invalidates the lint caches, so the new entries take effect on the next lint pass without any reload. - Atomic commit: every
register_*call made during a plugin's load (including from submodules imported from__init__.py) is captured in the registry snapshot. If__init__.pyraises before completing, all registrations from that plugin are reverted. The registry is never observed in a partially-loaded state by other plugins or by core. - Out of scope for rollback: non-registry side effects (file writes, env vars, threads spawned at import time, monkey-patches). Confine those to lazy paths invoked after a successful load.
- Test that load succeeded:
assert plugin_loader.get_load_failures() == []afterload_plugins(). A plugin that raised during load surfaces in that list with its filename and exception.
What ships with it
26 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.
- assets/generator-snapshots/tasks_external_task.xaml 4.5 KB
- assets/generator-snapshots/tasks_form_task.xaml 4.6 KB
- assets/generator-snapshots/tasks_task_management.xaml 4.9 KB
- assets/lint-test-cases/ac32-missing-form-file/Main.xaml 1.2 KB
- assets/lint-test-cases/ac32-missing-form-file/project.json 689 B
- assets/lint-test-cases/bad_create_form_task_no_folder.xaml 976 B
- assets/lint-test-cases/bad_external_task_subworkflow.xaml 941 B
- assets/lint-test-cases/bad_formtaskdata_data_late_binding.xaml 935 B
- assets/lint-test-cases/bad_invoke_method_targetobject_attribute.xaml 706 B
- assets/lint-test-cases/bad_large_inline_form_layout.xaml 3.0 KB
- assets/lint-test-cases/bad_persistence_in_foreach_string.xaml 1.4 KB
- assets/lint-test-cases/bad_persistence_in_foreachrow.xaml 1.4 KB
- assets/lint-test-cases/bad_persistence_subworkflow.xaml 995 B
- assets/lint-test-cases/bad_ui_invoke_method.xaml 740 B
- assets/lint-test-cases/bad_unrolled_sequential_tasks.xaml 4.0 KB
- assets/lint-test-cases/good_shadow_task_foreach.xaml 2.9 KB
- evals/tasks-battle-tests.md 16 KB
- extensions/__init__.py 13 KB runs code
- extensions/battle_test_grading.py 10 KB runs code
- extensions/generators.py 37 KB runs code
- extensions/lint_rules.py 32 KB runs code
- extensions/scaffold_hooks.py 720 B runs code
- references/external-tasks.md 8.4 KB
- references/form-tasks.md 22 KB
- references/task-management.md 7.4 KB
- references/version-profiles/UiPath.Persistence.Activities/1.4.json 12 KB
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.
- 2mo ago First seen · 139 lines · 138 tokens per session scan A b4aabfb04537
uipath-tasks is a skill published in the GitHub repository marcelocruzrpa/uipath-ai-skills (110 stars, last pushed 3mo ago), licensed MIT. It adds 138 tokens to every session and 2,970 once invoked, about $0.0006 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
hourly-rate-time
A time-management method based on assigning a high personal value to each hour. It treats time as a limited resource and uses that value to decide which tasks to do, outsource, or skip.
screen-detox
A habit-change framework for reducing non-work screen use such as social media, short videos, games, and endless scrolling.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
process
Process: retrospectives, session handoff, pair programming, subagent-driven development, condition-based waiting.
codebase-navigation
Use this skill when starting work in an unfamiliar codebase or area — finding where something is implemented, how a request flows, what depends on a piece of code, or where a change should go — before reading files one by one. Triggers: user says "where is", "how does this work", "find the code that", "explain this…