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-align-client-stylegit 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-align-client-style)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-align-client-style"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-align-client-style/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-align-client-style"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-align-client-style.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 | $0.00022 | $0.00547 |
| Opus 5.5 | $0.00009 | $0.00219 |
| Sonnet 5.5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
layerkit-align-client-style 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
layerkit-align-client-style
Before source edits, match the customer's package layout, DI, HTTP client, and test stack. Avoid orphan trees.
Protocol
- Scan customer repo (read-only) for existing integration clients:
- Java/TS/Python/etc.: package roots, DI/framework style, HTTP client, test stack, naming, error handling
- existing vendor clients, mappers, adapters, SDK wrappers, fetch/axios/WebClient/HttpClient usage
- multi-vendor packages: sibling vendor adapters, shared registry/router, and the sibling test pattern a new vendor should clone
- Deny-paths: same as discover (no
.env, secrets, keys, pem). - Build a style profile markdown:
# client-style-profile
- language: java | typescript | python | other
- basePackageOrModule: com.example.integrations | src/integrations
- moduleLayout: single-module | multi-module path
- di: spring | guice | plain ctor
- httpClient: OkHttp | WebClient | java.net.http
- json: jackson | gson
- logging: slf4j | ...
- test: junit5 + (wiremock|mockwebserver|mockito)
- naming: *Client / *Adapter / *Mapper
- errorHandling: checked | runtime + mapping notes
- multiVendor: yes|no; siblingReference: file://…; registry: file://…; newVendorFollows: <path pattern>
- examples: file://paths to 2–3 reference classes (prefer sibling vendor adapters when present)
- Write profile to memory (and optional file under projectDir).
Do this by reading representative source files directly. Deterministic rails may list files, but they must not infer the style profile for you.
Optional research note:
layerkit memory append --type research --title "client style profile" --vendor general --body-file ./client-style-profile.md
- Next: source-edit skill edits production entrypoints directly using this profile as evidence.
Forbidden
- Inventing a parallel package tree when an integration module already exists
- Reading secrets or copying credentials into the profile
- Generating production code in this skill (analysis only)
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 · 58 lines · 22 tokens per session scan A 73f4d13aae9c
layerkit-align-client-style is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 547 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
competitive-teardown
Systematic competitor analysis covering product teardowns, 12-dimension scoring rubric, feature comparison matrices, SWOT analysis, pricing model deconstruction, UX audits, and strategic action plans with stakeholder presentation templates.
contract-and-proposal-writer
Generate business documents — contracts, proposals, SOWs, NDAs, MSAs — with jurisdiction-aware clauses for US, EU, UK, and DACH. Use when starting client engagements, writing proposals, drafting agreements, or needing GDPR-compliant DPAs.
deal-desk
Deal desk: reviews, approves, and structures non-standard sales deals. Use when standing up a deal desk, building approval-threshold matrices, designing deal-review packets, routing deals, or auditing deals for compliance.
form-cro
Form optimization for lead capture, contact, demo request, application, and checkout forms. Covers field-cost analysis, multi-step form design, validation UX, mobile optimization, and A/B testing frameworks.
free-tool-strategy
Free tool marketing strategy covering idea evaluation, tool design, lead capture architecture, SEO landing pages, launch playbook, and ROI measurement for calculators, generators, checkers, graders, and interactive tools.
popup-cro
Popup and modal optimization for conversion. Covers exit-intent, slide-ins, banners, timing optimization, frequency capping, audience targeting, compliance, and A/B testing frameworks for lead capture, promotions, and announcements.