at_client_sdk is a collection of Dart SDKs, libraries, and Flutter widgets for building applications on the Atsign Platform. Developers use it for command-line tools, services, IoT devices, and mobile or desktop apps, and the catalogue skill supports work with the SDK.
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 atsign-foundation/at_client_sdk --skill at_client_skills-sdkgit clone --depth 1 https://github.com/atsign-foundation/at_client_sdkWrote 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/atsign-foundation/at_client_sdk/at_client_skills-sdk)<a href="https://agentmods.dev/skills/atsign-foundation/at_client_sdk/at_client_skills-sdk"><img src="https://agentmods.dev/badge/skills/atsign-foundation/at_client_sdk/at_client_skills-sdk/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/atsign-foundation/at_client_sdk/at_client_skills-sdk"><img src="https://agentmods.dev/badge/skills/atsign-foundation/at_client_sdk/at_client_skills-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 306 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 313 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 316 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 318 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Prompt Injection · line 530 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 532 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 533 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 534 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 535 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 536 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00232 | $0.05577 |
| Opus 5 | $0.00116 | $0.02789 |
| Sonnet 5 | $0.00046 | $0.01115 |
| Haiku 4.5 | $0.00023 | $0.00558 |
Grade A, and why
at_client_skills-sdk 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 11d 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 — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.
atsign-dart-sdk Skill
Audience: developers adding
at_client/at_client_flutterto their own Dart or Flutter app from pub.dev — not developers editing the SDK repo itself.
1. CRITICAL: Use the Modern Collection API
Always use AtCollection<T>. Never use AtCollectionModel.
// ✅ CORRECT — modern API
import 'package:at_client/at_client.dart';
final todos = await atClient.collection<Todo>(
'todos.my_app',
const Duration(days: 7),
fromJson: Todo.fromJson,
typeTag: 'Todo',
);
// ❌ WRONG — deprecated, do not use
class MyModel extends AtCollectionModel { ... } // @Deprecated("Use AtClient.collection...")
The entire AtCollectionModel hierarchy is annotated
@Deprecated("Use AtClient.collection for collection-style operations").
If asked how to use
AtCollectionModel: do NOT show anyAtCollectionModelcode, even in a "before/deprecated" comparison. Show ONLY theAtCollection<T>pattern above, state it is deprecated, and quote the@Deprecatedmessage.
Read references/01-deprecation-guide.md for the full migration table from old to new API.
2. Package Map
Install with dart pub add — it resolves the latest compatible version:
| Use case | packages to add |
|---|---|
| Dart CLI / server / IoT | at_client |
| Flutter app | at_client_flutter (re-exports at_client — one dep) |
| CLI / headless Dart | at_client, at_cli_commons |
| APKAM / custom auth flows | at_client or at_client_flutter, plus at_auth |
| Raw cryptographic operations | at_client or at_client_flutter, plus at_chops |
Never add: at_common_flutter, at_onboarding_flutter (discontinued — use
the at_client_flutter auth dialogs), at_backupkey_flutter,
at_invitation_flutter, at_sync_ui_flutter, at_theme_flutter
What ships with it
15 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.
- evals/evals.json 14 KB
- references/01-deprecation-guide.md 7.0 KB
- references/02-atcollection-api.md 11 KB
- references/03-query-api.md 9.4 KB
- references/04-events-api.md 8.7 KB
- references/05-flutter-auth.md 9.8 KB
- references/06-package-map.md 6.5 KB
- references/07-common-pitfalls.md 7.9 KB
- references/08-domain-object-patterns.md 7.0 KB
- references/09-testing-patterns.md 8.1 KB
- references/10-architecture-guide.md 7.2 KB
- references/11-sync.md 3.9 KB
- references/12-remote-atserver.md 6.5 KB
- references/13-rpc.md 4.2 KB
- references/14-multi-agent.md 6.2 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.
- 11d ago First seen · 563 lines · 232 tokens per session scan A 8d0192dfa3e4
at_client_skills-sdk is a skill published in the GitHub repository atsign-foundation/at_client_sdk (1,436 stars, last pushed today), licensed BSD-3-Clause. It adds 232 tokens to every session and 5,577 once invoked, about $0.0012 per session on Opus 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
dart-expert
Expert-level Dart, Flutter, mobile development, and cross-platform apps. Use when the user mentions Flutter, mobile, cross platform, or widgets, or when the task involves Dart Language or Flutter Framework.
building-flutter-apps
Flutter Riverpod app architecture and Windows installer delivery. Use before changing a Riverpod Flutter app/package or its Windows desktop packaging/update pipeline; skip non-Riverpod stacks and pure-Dart work.
implementing-openapi-in-dart
Reads an OpenAPI 3.0 specification and manually implements a type-safe Dart API layer using Dio for HTTP, Freezed or Equatable for models, and jsonserializable for serialisation. Use when given an OpenAPI/Swagger file (JSON or YAML) and asked to implement the API in Flutter/Dart, create Dart models from an API schema…
integrating-firebase
Firebase integration for Flutter including Auth, Firestore, FCM, Cloud Storage, Analytics, and Crashlytics. Use when implementing serverless backend features, real-time sync, or push notifications.
flutter-networking
Implement, fix, debug, review, or refactor Flutter networking code for HTTP/REST APIs, WebSocket realtime flows, authentication and token refresh, request headers, timeouts, retries, JSON parsing, caching, background isolates, repositories, services, and adaptation to existing http, Dio, Retrofit, Chopper, or custom…
nylo-auth
Use when implementing user authentication, login/logout flows, storing auth tokens, checking authentication state, managing multiple auth sessions, accessing device IDs, or configuring authenticated routes in a Nylo v7 Flutter app.