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 skills/leifericf/agentic-sdk/check-portabilitynpx skills add leifericf/agentic-sdk --skill check-portabilitygit clone --depth 1 https://github.com/leifericf/agentic-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/leifericf/agentic-sdk/check-portability)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/check-portability"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/check-portability.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00909 |
| Opus 5 | $0.00016 | $0.00454 |
| Sonnet 5 | $0.00007 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
check-portability 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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
check-portability
Role: review the shard for behavior that works on one platform but breaks on another.
Failure model: the code runs on the development platform and silently misbehaves on a committed platform, because a platform difference was not gated or a host-order assumption leaked.
Read the design docs for the project's platform commitments before sweeping. A platform the project does not commit to is out of scope.
Look for
- Platform branches not compile-time gated. A platform check that runs at runtime when it could fold away at compile time; a platform path that ships in a release build for a platform it does not target; a check that tests the wrong platform predicate.
- Filesystem semantics that differ. Case sensitivity, path separators, max path length, reserved names, mandatory versus advisory file locking, atomic-rename guarantees, permission models. Use the platform library's path handling; do not hand-roll. A path built with a hardcoded separator or a hardcoded home directory is a finding.
- Watcher and event-source divergence. When the project watches the filesystem or subscribes to OS events, the shape of the event differs across platforms (rename versus modify coalescing, latency guarantees, recursive defaults). A body that assumes one platform's semantics and breaks on the other is a finding.
- Surface and windowing creation. Graphics or window surface creation is platform-specific. The surface code must gate the right path per platform. A call to the wrong platform's surface creator is a build failure, not a finding; an unused but compiled surface path that pulls the wrong system framework is.
- System-library availability. A decoder or integration that uses a system library on one platform and a bundled library on another. The dispatch must be platform-aware; a path that assumes the system library will not work where it is absent.
- Endianness and integer widths. External formats (file headers,
wire protocols, serialized state) have specific byte orders; a
host-order reinterpret is a finding. Pointer widths and the C
fixed-width types (
c_int,c_long,long) differ across platforms; a type whose width varies, used in a persistence or wire shape, is a finding. Use fixed-width types at every external boundary. - Baked artifact portability. A build that produces a platform- specific artifact (a dylib, a shared object, an executable) must target every platform the project commits to, and the runtime must select the right one for the host. A bake that produces one platform only and tries to load it on another is a build-config finding.
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.
- 5d ago First seen · 96 lines · 33 tokens per session scan A 1f608dacf446
check-portability is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 909 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…