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 hariharapanigrahy/layerkit --skill layerkit-inventory-surfacesgit clone --depth 1 https://github.com/hariharapanigrahy/layerkitWrote 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/hariharapanigrahy/layerkit/layerkit-inventory-surfaces)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-inventory-surfaces"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-inventory-surfaces/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/hariharapanigrahy/layerkit/layerkit-inventory-surfaces"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-inventory-surfaces.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 | $0.00032 | $0.00522 |
| Opus 5.5 | $0.00013 | $0.00209 |
| Sonnet 5.5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
layerkit-inventory-surfaces 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 1mo 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.
What it actually says
layerkit-inventory-surfaces
Before research/source-edit on a multi-language package, list every language or surface the package supports so Layerkit can block PR/handoff until each is updated or explicit residual.
This step is required for heal and full. Domain discover may be skipped on heal; surfaces is never skipped.
Protocol
- Walk the package (source:code): e.g.
**/server/node,server/python,server/ruby,server/php*,server/java,server/go,server/dotnet,server/nextjs, client UIs. - Write session inventory:
{projectDir}/memory/runbooks/surface-inventory.json
{
"schemaVersion": 1,
"package": "org/repo",
"languages": [
{
"id": "node",
"roots": ["fixed-price-subscriptions/server/node"],
"status": "pending"
},
{
"id": "python",
"roots": ["fixed-price-subscriptions/server/python"],
"status": "pending"
}
],
"notes": "Inventoried from package layout; source:code"
}
- Put the same JSON (or a pointer + summary) in mark-done
--evidence. - Later, during source-edit, update each language:
"status": "updated"+"paths": ["…/server.js"]when production files for that language were changed, or"status": "residual"+"residual": "why not changed (SDK gap, out of scope, …)"
- Layerkit rejects source-edit complete / handoff while any language is still
pending.
Forbidden
- Listing only one language when the package clearly has more (freestyle single-lang heal)
- Marking
updatedwithout real paths - Marking
residualwithout a concrete residual reason - Skipping this step on heal
Success
-
surface-inventory.jsonexists with ≥1 language and non-emptyroots[] - Evidence cites package layout (source:code)
- Agent understands that multi-lang completeness is enforced before PR
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.
- 1mo ago First seen · 59 lines · 32 tokens per session scan A d3e18be92643
layerkit-inventory-surfaces is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 522 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
ultracite
Ultracite is a zero-config linting and formatting preset for JavaScript/TypeScript projects. Use when: (1) Setting up or initializing Ultracite in a project, or migrating its existing lint and format config onto Ultracite (ultracite init), (2) Running linting or formatting commands (check, fix, doctor), (3) Writing or…
prismer-python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
loom-swift
Swift language expertise for idiomatic, production-quality code.
loom-dart
Dart language expertise for idiomatic, production-quality code.
loom-c
C language expertise (C11/C17/C23) for memory-safe, portable, production-quality systems code.