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 commands/nasrulhazim/claude/erdgit clone --depth 1 https://github.com/nasrulhazim/claudeWrote 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/commands/nasrulhazim/claude/erd)<a href="https://agentmods.dev/commands/nasrulhazim/claude/erd"><img src="https://agentmods.dev/badge/commands/nasrulhazim/claude/erd.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 | $0.00013 | $0.01014 |
| Opus 5 | $0.00006 | $0.00507 |
| Sonnet 5 | $0.00003 | $0.00203 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
erd 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 6d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/erd Command
Drives the schema-diagram skill. Load it first — it carries the templates, the traps and the
verification checklist:
Skill: schema-diagram
Subcommands
| Command | Does |
|---|---|
/erd |
Detects what exists and picks the right path below |
/erd init |
Scaffolds the whole toolchain into a project that has none |
/erd generate |
php artisan docs:erd — reads the live database into the JSON payload |
/erd build |
npm run build:erd — bundles the JSON into the standalone HTML |
/erd refresh |
Generate + build + stage both outputs. The everyday command after a migration |
/erd check |
php artisan docs:erd --check — domain coverage gate, writes nothing |
/erd domains |
Review or extend the domain map without touching anything else |
/erd verify |
Open the built document and walk the skill's verification checklist |
/erd with no argument
- Does
app/Support/Erd/ErdSchema.phpexist?- No → this is
/erd init. Confirm with the user before scaffolding. - Yes → continue.
- No → this is
- Is the database at head?
php artisan migrate:status | tail -5- Behind → do not migrate their database. Build in a throwaway, drop it afterwards, and say so in the summary. A diagram of a half-migrated schema is worse than none, but a surprise migration is worse than both.
- Run
/erd refresh.
/erd init
Do not scaffold silently — this writes ~10 files and adds four npm dependencies.
- Confirm the target docs path (default
docs/03-architecture/). - Draft the domain map and show it to the user before writing it. This is the only part
that takes judgement; everything after is mechanical. Aim for 8–14 domains named after the
product's own nouns, with framework tables in one
systemdomain. - Copy the extractor, the domain map, the React Flow island and the stylesheet from the skill's reference files.
- Set
PRODUCTinErdBoard.jsxandAbout.jsx; set the brand faces inerd.css. - Rewrite the prose in
About.jsxfor this product — it is the first thing anyone reads. - Install deps, generate, build, verify.
- Write the companion
docs/03-architecture/03-database-erd.md— the HTML is not reviewable in a PR, does not render on GitHub, and does not appear in a grep. - Add
tests/Feature/Docs/ErdDomainCoverageTest.phpso the map fails the suite, not the reader.
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.
- 6d ago First seen · 90 lines · 13 tokens per session scan A 9f07185b84e8
erd is a command published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 1,014 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 2026-08-30.
Other commands, from other repositories
review-renovate
Review and merge renovate PRs with automerge configuration updates.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
plan-regression-tests
Plan regression tests for existing code with it.skip statements.
init
Initialize configurations for Supabase local development.
volume-admin-set-status
Changes the operational status of a named volume.
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.