Agent skill · Audited from source
axiom-health
skill · charleswiltgen/axiomMIT licenceAudited 28 Oct 2026 · source 2a84b9c2c3eb
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 2a84b9c2c3eb and found no filesystem, network or shell access and no hard-coded secrets. What it does: Use when working with HealthKit, WorkoutKit, health data, workouts, or fitness features on iOS or watchOS. Covers permissions, queries, background delivery, custom workouts, multidevice coordination.
Cite
Cite this page
ModelsAtlas. “axiom-health (charleswiltgen/axiom)”. Retrieved 28 Oct 2026. https://modelsatlas.com/skills/charleswiltgen/axiom-health
Trust audit
Audit 0.4.1 · source read 28 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 1 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (1)
INFOPrompt injectionprompt.authority_framing · skills/authorization-and-privacy.md:195
**The result is sparse, and that is the trap.** A type appears in the dictionary **only** when the user granted *limited* read access with a specific earliest date. Types without a limited-access date
- Why
- No further detail recorded for this rule.
- Fix
- —
Audit 0.4.1 · source sha 2a84b9c2c3eb · 28 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishercharleswiltgen GitHub userOwner of the repository this skill is read from
- Source foldercharleswiltgen/axiom/axiom-codex/skills/axiom-healthThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict2a84b9c2c3ebA new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Use when working with HealthKit, WorkoutKit, health data, workouts, or fitness features on iOS or watchOS. Covers permissions, queries, background delivery, custom workouts, multidevice coordination.
---
name: axiom-health
description: Use when working with HealthKit, WorkoutKit, health data, workouts, or fitness features on iOS or watchOS. Covers permissions, queries, background delivery, custom workouts, multidevice coordination.
license: MIT
---
# HealthKit and WorkoutKit
**You MUST use this skill for ANY HealthKit or WorkoutKit development including authorization, data queries, background delivery, workout sessions, planned workouts, wellbeing APIs (State of Mind), Medications, and Health Records.**
## Quick Reference
| Symptom / Task | Reference |
|----------------|-----------|
| HealthKit framework model, `HKHealthStore`, data types, sample vs characteristic data | See `skills/fundamentals.md` |
| Capability setup, `requestAuthorization`, purpose strings, read-asymmetry, privacy | See `skills/authorization-and-privacy.md` |
| `HKSampleQuery`, Swift Concurrency query APIs, `HKStatisticsCollectionQuery`, sample writes | See `skills/queries.md` |
| Anchored queries, observer queries, `HKDeletedObject`, `background-delivery` entitlement | See `skills/sync-and-background.md` |
| `HKWorkoutSession`, `HKLiveWorkoutBuilder`, recovery, multi-device, iOS/iPadOS/watchOS workout tracking | See `skills/workouts.md` |
| Workout zones (heart-rate/power effort bands), live + retrospective `OS27` | See `skills/workouts.md` |
| WorkoutKit custom/planned workouts, scheduling, swimming workouts, previewing | See `skills/workoutkit.md` |
| State of Mind, Medications API, symptom logging, menopausal state, wellbeing APIs `OS27` | See `skills/wellbeing-and-medications.md` |
| Health Records (FHIR), Mobility Health App, motion-based health | See `skills/clinical-and-mobility.md` |
## Cross-Suite Routes
These topics overlap with HealthKit/WorkoutKit but live in separate suites:
#### watchOS presentation
- Watch-specific workout presentation (Always On, Smart Stack), complication surfaces → See axiom-watchos
- Workout app structure on Apple Watch → See axiom-watchos (`skills/platform-basics.md`)
#### Concurrency
- Swift 6 concurrency, actors, Sendable → See axiom-concurrency
- HealthKit queries bridging to Swift Concurrency → `skills/queries.md` is the canonical example
#### SwiftUI
- Charts rendering for health data → See axiom-swiftui
- `@Observable` view models for health data → See axiom-swiftui
#### Data and sync
- General cross-platform sync patterns (CloudKit, GRDB) → See axiom-data
- HealthKit anchored/observer queries as a generalizable sync mechanism → `skills/sync-and-background.md`
#### Security and privacy
- Keychain storage, encryption, data-protection entitlements → See axiom-security
## Conflict Resolution
**axiom-health vs axiom-watchos**: For workout apps on Apple Watch:
1. **Use axiom-health** for `HKWorkoutSession` lifecycle, `HKLiveWorkoutBuilder`, recovery APIs, multi-device mirroring — these are HealthKit concepts, not watch concepts
2. **Use axiom-watchos** for watch-specific presentation: Always On display, Smart Stack placement, watchOS background mode coordination
3. **Both apply** for a watch-native workout app — start with axiom-health for session lifecycle, then axiom-watchos for presentation
**axiom-health vs axiom-concurrency**: For HealthKit query patterns:
1. **Use axiom-health** for which query type to choose and HealthKit-specific gotchas
2. **Use axiom-concurrency** for general Swift 6 actor isolation rules that apply to query callbacks
**axiom-health vs axiom-data**: For change-tracked data synchronization:
1. **Use axiom-health** for `HKAnchoredObjectQuery`, `HKObserverQuery`, `HKDeletedObject`
2. **Use axiom-data** for application-level data sync across devices (CloudKit, GRDB, SwiftData)
## Decision Tree
```dot
digraph health {
start [label="HealthKit / workout task" shape=ellipse];
what [label="What area?" shape=diamond];
start -> what;
what -> "skills/fundamentals.md" [label="framework basics, data types"];
what -> "skills/authorization-and-privacy.md" [label="permissions, purpose strings, privacy"];
what -> "skills/queries.md" [label="reading data, rollups, writes"];
what -> "skills/sync-and-background.md" [label="change tracking, background delivery"];
what -> "skills/workouts.md" [label="HKWorkoutSession, live workouts"];
what -> "skills/workoutkit.md" [label="planned/custom workouts"];
what -> "skills/wellbeing-and-medications.md" [label="State of Mind, Medications"];
what -> "skills/clinical-and-mobility.md" [label="Health Records, Mobility"];
what -> "axiom-watchos" [label="watch-specific presentation"];
what -> "axiom-concurrency" [label="general actor isolation rules"];
what -> "axiom-swiftui" [label="Charts, data visualization"];
}
```
## Resources
**WWDC**: 2019-218, 2020-10182, 2020-10184, 2020-10664, 2021-10009, 2021-10287, 2022-10005, 2023-10016, 2023-10023, 2024-10084, 2024-10109, 2025-321, 2025-322
**Docs**: /healthkit, /healthkit/about-the-healthkit-framework, /healthkit/authorizing-access-to-health-data, /healthkit/protecting-user-privacy, /healthkit/reading-data-from-healthkit, /healthkit/running-queries-with-swift-concurrency, /healthkit/executing-anchored-object-queries, /healthkit/executing-observer-queries, /healthkit/hkworkoutsession, /healthkit/hklivewobuilder, /workoutkit, /healthkit/accessing-health-records
**Skills**: axiom-watchos, axiom-concurrency, axiom-swiftui, axiom-data, axiom-securityExcerpt, first 5,423 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit 2a84b9c
git clone https://github.com/charleswiltgen/axiom git -C axiom checkout 2a84b9c2c3eb
The author documents no install command, so this uses the repository directly. Our verdict covers commit 2a84b9c2c3eb only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
2a84b9c2c3eb
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/charleswiltgen/axiom-health/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
obra/superpowers
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions…
obra/superpowers
Use when you have a spec or requirements for a multi-step task, before touching code
obra/superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Add this badge to your README
[](https://modelsatlas.com/skills/charleswiltgen/axiom-health/)
<a href="https://modelsatlas.com/skills/charleswiltgen/axiom-health/"><img src="https://modelsatlas.com/skills/charleswiltgen/axiom-health/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about axiom-health
What does the axiom-health skill do?
Is axiom-health safe to install?
What can axiom-health access on my machine?
How current is this page?
Sources
- github.com/charleswiltgen/axiom/tree/main/axiom-codex/skills/axi — the audited source at commit 2a84b9c2c3eb and every finding aboveObserved · 28 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the axiom-health skill do?
- Is axiom-health safe to install?
- What can axiom-health access on my machine?