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 David405/harness-kit --skill erd-authoringgit clone --depth 1 https://github.com/David405/harness-kitWrote 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/david405/harness-kit/erd-authoring)<a href="https://agentmods.dev/skills/david405/harness-kit/erd-authoring"><img src="https://agentmods.dev/badge/skills/david405/harness-kit/erd-authoring/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/david405/harness-kit/erd-authoring"><img src="https://agentmods.dev/badge/skills/david405/harness-kit/erd-authoring.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 | $0.00090 | $0.00828 |
| Opus 5.5 | $0.00036 | $0.00331 |
| Sonnet 5.5 | $0.00018 | $0.00166 |
| Haiku 4.5 | $0.00009 | $0.00083 |
Grade A, and why
erd-authoring 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 2mo 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ERD authoring
Kit-owned. Edit in the harness-kit repo, not in the consumer repo.
Profile: product-erd. The step before contracts exist. Produces erd.md +
architecture.md, and a FEATURES.json seed that turns each slice into a sprint contract.
When to use
A new product or service, a new domain, or a contract crossing teams or repos.
Where it sits in the loop
BOOT → **ERD?** → RESEARCH? → CONTRACT. Step 2 is a routing test with three conditions (see the
agent process). This skill carries its own discovery research in S0; the loop's RESEARCH? is
contract-scoped and comes after. Never dual-run them.
When not to use
A feature inside an already-documented service goes straight to sprint-contract. This stage
is expensive by design; running it on ordinary work is ceremony. Not the same as optional RESEARCH:
RESEARCH distills open questions for one contract, this produces a durable document feeding many.
The five stages — stop at every gate
The agent stops at every gate and waits for a human. Do not run stages together.
| Stage | Produce | Gate |
|---|---|---|
| S0 Frame | Input inventory (brief, PRD, designs, tickets, related repos, code to reuse); executive summary; goals; non-goals | Human confirms the scope boundary |
| S1 Decisions | Every decision the ERD must lock — Topic | Options | Recommendation | Status. No design written yet |
Human locks or defers each; deferrals become Open Questions with an owner and needed-by |
| S2 Design | architecture.md — mental model, diagram, boundaries, control flows, data ownership |
Human confirms the shape |
| S3 Contracts | ERD design sections: standards, API/event/data contracts, error model, acceptance criteria, risks | Human confirms contracts and falsifiable criteria |
| S4 Slices | Implementation plan: Feature slices plus the FEATURES.json seed |
Human PASS |
S1 is the load-bearing stage. Decisions elicited before prose is written are decisions that do not resurface later as a string of one-line lock contracts, or as reversals of already-written text.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 64 lines · 90 tokens per session scan A 371c7bc82fc3
erd-authoring is a skill published in the GitHub repository David405/harness-kit (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 828 once invoked, about $0.0004 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
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
dev-runtime
How the Node side of a dev stack runs without haven, and the backend host: pnpm dev (UI built once, backend reloading), pnpm dev:hmr (adds the Vite ui lane), tools/dev-runtime (api + worker in one Node process), backend reload on a file change, the debounce (quiet window + max wait), ports derived from PORT. Use when…
api-design
Use when settling the contract of an API you expose, before implementation: resources/URLs, REST vs GraphQL, versioning, one RFC 9457 error envelope, pagination, idempotency — emitted as OpenAPI 3.1. NOT implementing the endpoints (that is fastapi/nestjs/go/nodejs), NOT auth hardening (that is secure-coding), NOT…