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/test-coveragegit clone --depth 1 https://github.com/UiPath/skillsWhat 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 | $0.00000 | $0.16078 |
| Opus 5 | $0.00000 | $0.08039 |
| Sonnet 5 | $0.00000 | $0.03216 |
| Haiku 4.5 | $0.00000 | $0.01608 |
Grade A, and why
test-coverage 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 2d 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 — 797 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UiPath Skills Test Coverage Report
Analyze what a skill teaches vs what its tests verify. Produce a gap analysis with prioritized recommendations.
Input: $ARGUMENTS
- Skill name or path (e.g.,
uipath-maestro-flow) — single skill. - Empty or
all— every skill underskills/.
Output: Markdown report(s) in tests/reports/<skill-name>.md (e.g., tests/reports/uipath-maestro-flow.md), unless the user specifies a different path. Overwrite existing reports at the same path.
Feed-forward contract. This report is the primary input to /generate-task <description>. /generate-task takes a free-form description and infers the target skill from it — write gap titles as self-contained descriptions that name the skill or its CLI surface, so the reader can paste a gap straight into /generate-task (e.g. "Brown-field editing of existing uipath-maestro-flow projects" → /generate-task Brown-field editing of existing uipath-maestro-flow projects).
Phase 1 — Discovery
- Resolve target skill(s):
- Single name →
skills/<name>/. Ifskills/<name>/does NOT exist but<name>is in the Planned Skills Registry below, treat it as a planned skill (use the planned-skill template in Phase 5). If<name>is in the Cross-Cutting Capability Registry below, treat it as a cross-cutting capability (see that section). - Empty/all → union of (a) glob
skills/uipath-*/, (b) every entry in the Planned Skills Registry whose folder does not yet exist, and (c) every entry in the Cross-Cutting Capability Registry. Planned-but-missing skills MUST appear in the per-skill report set and roll-up at 0% until they ship; cross-cutting capabilities MUST appear as their own report + roll-up row (flagged cross-cutting, see §4f and §5).
- Single name →
- For a normal skill, check for
tests/tasks/<skill-name>/. For a cross-cutting capability, there is no dedicated dir — discover its tests by tag (step 3). - Find
*.yamltest files. Normal skill: recursively undertests/tasks/<skill-name>/, exclude_shared/. Cross-cutting capability:grep -rl '<tag>' tests/tasks --include='*.yaml' | grep -v _sharedacross the wholetests/tasks/tree (its tasks live inside other skills' dirs). - Find
check_*.pyscripts recursively. Exclude_shared/test_*.py(unit tests for shared helpers).
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.
- 2d ago First seen · 797 lines · 0 tokens per session scan A 173bc6a70ac5
test-coverage is a command published in the GitHub repository UiPath/skills (150 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 16,078 tokens. 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 commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
memory-store
Store an insight, decision, or pattern to memory.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".