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/david405/harness-kit/erd-authoringnpx 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.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 | $0.00090 | $0.00828 |
| Opus 5 | $0.00045 | $0.00414 |
| Sonnet 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 4d 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.
- 4d 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 6d ago), licensed Apache-2.0. It adds 90 tokens to every session and 828 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…