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 makifbaysal/tasktrooper --skill offline-syncgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/offline-sync)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/offline-sync"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/offline-sync/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/makifbaysal/tasktrooper/offline-sync"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/offline-sync.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00050 | $0.00745 |
| Opus 5.5 | $0.00020 | $0.00298 |
| Sonnet 5.5 | $0.00010 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
offline-sync 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 8d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offline and Sync
Overview
Treat "offline" as a normal state, not an error condition: a screen that only works with a live connection is a defect on mobile. The hard part isn't detecting offline — it's making a queued mutation replay exactly once and keeping the UI honest about what's actually saved.
Local store
Follow the repo's existing choice (drift/sqflite for Flutter, Room for Android, SwiftData/Core Data for iOS) — don't introduce a second local-storage mechanism alongside one that's already there.
Outbox pattern
- Queue mutations in a local outbox table when offline; replay on reconnect.
- Every queued mutation carries a client-generated idempotency key, sent with the eventual request, so a retried replay (after a crash mid-sync, or a flaky connection that "succeeded" without the ack arriving) is deduplicated server-side instead of double-applied.
- Connectivity plugins (
connectivity_plusand equivalents) report the state of the network interface, not whether the server is actually reachable — treat the server's response as the source of truth for whether a request succeeded, not the interface state alone.
Background replay
- Android:
WorkManager(native) or theworkmanagerplugin (Flutter) for replay that must survive the app being backgrounded or killed. - iOS:
BGTaskSchedulerfor background replay — register and schedule it, and test on-device since the simulator's background scheduling is unreliable.
UI honesty
Show sync status explicitly per item — pending / syncing / failed — never render an unsynced change as if it were already saved. A spinner that never resolves is worse than an honest "failed, tap to retry."
Conflicts
Pick one conflict rule per data type (last-write-wins, or an explicit user choice when both sides changed) and write it down in the task — don't leave it implicit in the code for the next person to infer.
Reads degrade gracefully
Cached data with a staleness indicator beats a spinner that never resolves — show what you have, mark it as possibly stale, and update when the network returns.
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.
- 8d ago First seen · 57 lines · 50 tokens per session scan A 08cf7683aacb
offline-sync is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 745 once invoked, about $0.0002 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 2026-10-05.
Other skills, from other repositories
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
nemo-fabric-integrate
Use this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python SDK — translating the consumer's own application, job, or deployment config into an in-memory FabricConfig, choosing the single-invocation convenience API or an explicitly…
ambient-healthcare-agent-with-nemotron-voice-agent
Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend.
earth2studio-create-datasource
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.
nemo-fabric-build-adapter
Build, migrate, review, and maintain third-party NVIDIA NeMo Fabric adapters against the public adapter contract. Use when creating adapter or target descriptors, mapping AgentConfig into an agent harness or custom-agent runtime, implementing start/invoke/stop, declaring schemas and capabilities, packaging discovery…
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.