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-multi-agentnpx skills add hariharapanigrahy/layerkit --skill layerkit-multi-agentgit 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-multi-agent)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-multi-agent"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-multi-agent.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 | $0.00020 | $0.00471 |
| Opus 5 | $0.00010 | $0.00235 |
| Sonnet 5 | $0.00004 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
layerkit-multi-agent 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 3d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
layerkit-multi-agent
Team of agents on the same integration pipeline. The lead agent coordinates specialists directly; Layerkit does not generate a deterministic multi-agent plan.
Start
Contract heal (map already exists — human supplies OpenAPI/docs)
- Discover task omitted
- Researcher = evidence-backed semantic rename decisions when needed
- If only docs are supplied, researcher/AI must read/cite docs before source edits
- AI agents edit production source/test files directly
- Record rename decisions in the handoff note only when docs/code evidence supports a removed-to-added field rename
First-time / multi-vendor
Use the lead agent to assign vendors/files explicitly. Keep one writer per production file and use handoff notes for state.
Roles
| Role | Skill | Heal note |
|---|---|---|
| orchestrator | orchestrate-integration | status shows mode=heal|full |
| discoverer | discover-data-layer | not in heal plan |
| stylist | align-client-style | topology for existing adapters |
| researcher | research-vendor | contract pin + drift |
| designer / author | design / processor | surgical on drift |
| privacy | privacy-review | human if new PII |
| integrator | source-edit-client | direct production source edits |
| verifier | doctor + project tests | quality |
| checker | checker-assist | read-only |
Concurrency
- Parallel research/integrate per vendor when files do not overlap
- Single writer:
integrator:registry - Human: privacy, checker approval, breaking drift
Forbidden
- Two agents on the same registry file
- Re-running full discover on heal when domain is known
- Invented fields or guessed renames; self-approve
- Treating generated plans as production source code
- Relying on Layerkit runtime/route/strategy code instead of editing the client package
Success
- Agent assignments match intent (heal vs full)
- Specialists have explicit files/responsibilities
- Production adapters updated
- Project tests + quality green
- Human checker handoff complete
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.
- 3d ago First seen · 59 lines · 20 tokens per session scan A 9a6446a7b127
layerkit-multi-agent is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 27d ago), licensed MIT. It adds 20 tokens to every session and 471 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…
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.
systematic-debugging
Skill "systematic-debugging" from Leodorareluctant259/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.