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/hariharapanigrahy/layerkit/layerkit-design-integrationnpx skills add hariharapanigrahy/layerkit --skill layerkit-design-integrationgit 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-design-integration)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-design-integration"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-design-integration.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 | $0.00029 | $0.00726 |
| Opus 5 | $0.00015 | $0.00363 |
| Sonnet 5 | $0.00006 | $0.00145 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
layerkit-design-integration scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. List required operations (from OpenAPI/curl) and which intents they serve. How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
layerkit-design-integration
Decide how to integrate after research: flat map vs multi-step flow. Record the design before authoring.
Decision tree
| Situation | Choose |
|---|---|
| Single endpoint, one payload per event, no branching | Linear VendorMap |
| OAuth/token then POST, multi-call sequence | Flow (call + assign + responseInto) |
| Cart line fan-out / batch chunks | Flow (foreach + optional batch_chunks) |
| Intent-specific routes or predicates | Flow (route / if) |
| Simple intents + multi-step intents for same vendor | Hybrid |
| PII before egress | Map or flow + privacy node / policy |
Default: prefer flat map. Introduce flow only when sequence, branching, or multi-call is required by evidence.
Protocol
- Read research memory + domain_spec for the vendor.
- List required operations (from OpenAPI/curl) and which intents they serve.
- Choose shape:
linear_map|flow|hybrid(map for simple intents, flow for multi-step). - Emit a design decision artifact (preferred CLI):
# compute shape from signals (sequence/branch/foreach/oauth/multi-call)
layerkit design decide --vendor <vendor> \
[--sequence] [--branch] [--foreach] [--oauth] [--multi-call] \
[--intent purchase]... [--evidence https://docs.example/...]... \
[--shape linear_map|flow|hybrid] [--out memory|path] [--json]
Writes {projectDir}/memory/runbooks/design-<vendor>.md (and optional companion JSON with --json).
- Sketch design (ids only — no invented field names):
shape: linear_map | flow | hybrid
vendor: <id>
intents: [...]
operations: [operationId → method path]
batch: none | foreach products[] | batch_chunks N
auth_steps: none | token_then_post
privacy: pre-egress policy required? yes/no
evidence: [urls / file://]
open_questions: [...]
- Also keep a short proposals note if useful:
layerkit memory append --type proposals --title "<vendor> integration design" --vendor <vendor> --body-file ./design.md
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 · 79 lines · 29 tokens per session scan A 49ecfd8099ab
layerkit-design-integration is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 28d ago), licensed MIT. It adds 29 tokens to every session and 726 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bcc-plan-spar
BCC align+lock+review PLAN.md for one slice (no product code). Slash: /bcc-plan-spar · chat: bcc:plan-spar · "lock PLAN" · spar the plan. Args: rounds=N (auto-review cap), review=self|subagent|cli|auto|off. Grill until clear enough (no default Q&A quota). Hand off to bcc-clean-cut after human APPROVE.
bcc-throughline
BCC global progress cockpit (plans.md/progress.md/findings.md). Slash: /bcc-throughline · chat: bcc:throughline · "where are we" · reprioritize · resume after /clear. Not for coding or full PLAN grill.
bcc-breaking-coding-chaos
BCC main skill: dual-loop coding workflow (throughline → plan-spar → clean-cut) or quick status+next. Slash: /bcc-breaking-coding-chaos · chat: bcc:breaking-coding-chaos · "run BCC" · "BCC status" · "what next BCC". Needs a real idea (1:1 implement). Args: goal text, or status. May pass plan-spar review budget as…
bcc-clean-cut
BCC minimal implement from locked PLAN.md (ponytail ladder + verify). Slash: /bcc-clean-cut · chat: bcc:clean-cut · "implement PLAN" after human APPROVE. Not for plan grill (use bcc-plan-spar).
chinese-git-workflow
适配国内 Git 平台和团队习惯的工作流规范——Gitee、Coding、极狐 GitLab 全覆盖.
chinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化.