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-factoringnpx skills add leifericf/agentic-sdk --skill check-factoringgit 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-factoring)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/check-factoring"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/check-factoring.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 | $0.00036 | $0.01109 |
| Opus 5 | $0.00018 | $0.00554 |
| Sonnet 5 | $0.00007 | $0.00222 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
check-factoring 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
check-factoring
Role: review the shard's structure.
Failure model: the code is correct but lives in the wrong place, so a branch cannot reach it, a boundary leaks, or two copies drift apart.
The authority is skills/shared/references/architecture.md (Functional
Core / Imperative Shell, dependency direction inward, the pure, shell,
and native-wrapper split). The placement source is the descriptor's
:architecture :modules map (see
skills/shared/references/project-descriptor.md).
Look for
- Dependency-direction violations. A pure function that calls an effectful one (IO, state, platform, persistence, a native handle); the effectful callee may sit in the same module or another; the rule is at the function, not the module, since modules are cut by domain and may hold both. An effectful function that threads another module's live state where only data should cross; a cycle between two modules that are therefore one domain or have the boundary drawn wrong. A pure function may not know an effect exists.
- Pure/effect and native leakage. IO, a clock, a global, a native call, a persistence write, or state mutation inside a PURE FUNCTION. A module that mixes pure and effectful functions is NOT a leak; modules are domain-based. Or pure decision logic (query construction, view-spec computation, plan or transaction-data building) buried inside an effectful function where a test cannot reach it. Or domain logic inside a native wrapper (the wrapper marshals; it does not decide).
- Native edge leakage. A wrapper that reaches into a handle's internals from the calling language, or that holds domain logic instead of marshalling data in and data out. Handles are opaque; the calling language passes them back, never inspects them.
- Duplication. The same nontrivial logic in two units. Cite both sites. The high-risk case is a new variant of an existing path: a second codec beside the first, a second transport beside the first, a windowed path beside the headless one. Check that it shares the existing machinery rather than copying it. A duplicated path drifts; the two must match and silently will not. Cite the original it should have reused.
- Oversized units. Files past the project's size gate (the descriptor's QA lane carries the threshold when one is set; absent one, roughly 800 lines for a file, 200 for a function). The carve-out: a file split along a domain seam is fine; a file growing by accretion is a finding.
- Mixed concerns. A function that builds data and applies the effect; a native body that allocates, computes, and reports; a handler that decides and persists. The core and shell split exists to separate these.
- Decisions trapped in effect loops. A semantic choice inlined in an event loop or a callback when it could be a returned value the caller switches on (description, not instruction). The inverse is equally a finding: a wrapper layer introduced only to fake purity or enable mocking, when a direct data read in decision code is correct.
- Dead structure. Public functions with one caller; parameters every caller passes identically; a record or struct that wraps a map without adding behavior.
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 · 107 lines · 36 tokens per session scan A 146ec8e769bd
check-factoring is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 1,109 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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…