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-flownpx skills add hariharapanigrahy/layerkit --skill layerkit-design-flowgit 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-flow)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-design-flow"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-design-flow.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 5.1 | $0.00027 | $0.00510 |
| Opus 5 | $0.00014 | $0.00255 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
layerkit-design-flow 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
layerkit-design-flow
Use this skill to decide how the client package should express a vendor integration change.
Protocol
- Read the existing integration topology: mappers, adapters, routers, registries, tests, and feature flags.
- Read vendor evidence for the changed endpoint, payload, auth, batching, or ordering requirement.
- Prefer changing the existing mapper/adapter path.
- Use a multi-step flow in client code only when vendor evidence requires sequencing, branching, batching, or retries that are not already represented.
- Before adding a new abstraction, document why the existing abstraction cannot be changed.
- Update tests around the actual production path.
Design Outputs
- Existing file/function to update.
- Stale code/docs/tests to delete or rewrite.
- Required source edits.
- Tests to add or update.
- Residual TODOs where the client datalayer cannot satisfy the vendor contract.
Multi-vendor / new vendor on existing path
When the package already ships one or more vendors and the user wants a new vendor:
- Pick a sibling vendor adapter/mapper as the structural reference (
file://path). - Design the new integration by following that existing path: same module root, registry/router wire, privacy hooks, and test layout.
- Prefer cloning the sibling structure over inventing a parallel facade or side registry.
- Document: sibling reference path → new vendor files → registry entry → tests cloned from sibling.
- Only introduce a new abstraction when no sibling file can own the vendor-specific behavior, and list what existing surface cannot be extended.
Forbidden
- Designing a Layerkit runtime flow instead of client-owned source code.
- Adding a side registry/facade when the existing route/mapper can be edited.
- Inventing auth, endpoint, batching, or routing behavior without evidence.
- Finalizing while package verification fails.
- Designing a freestyle tree beside an existing multi-vendor module root.
Success Criteria
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 · 52 lines · 27 tokens per session scan A acf18d914b71
layerkit-design-flow is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 510 once invoked, about $0.0001 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
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.