brd-ground

brd-ground is a command for Claude Code from ihudak/ihudak-claude-plugins. It costs 186 tokens per session (16,127 once invoked), scanned A, original, MIT.

A review workflow that checks a BRD's requirements against the actual source code and exported design screens. A BRD is a business requirements document describing what a product should do.

In plain words
What is it for?
Use it to verify requirements against pinned code versions and design assets, with optional checks for related documents, dependencies, and a derivation matrix.
Why use it?
It catches requirements based on outdated, incomplete, or unsupported assumptions. It also requires findings to be independently checked before treating them as evidence.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dev-workflows plugin — 2 skills, 28 commands, 38 agents, 3 hooks shipped together

Good fit Use it to verify requirements against pinned code versions and design assets, with optional checks for related documents, dependencies, and a derivation matrix.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ihudak/ihudak-claude-plugins
Claude Code
/plugin install dev-workflows

Made for: Claude Code.

Or install dev-workflows, the plugin that ships this one along with the rest of its 2 skills, 28 commands, 38 agents, 3 hooks.

Wrote 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.

agentmods badge for brd-ground

README.md
[![agentmods](https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/brd-ground/github.svg)](https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/brd-ground)
Your own site
<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/brd-ground"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/brd-ground/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.

agentmods 80×15 button for brd-ground

Your own site · 80×15
<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/brd-ground"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/brd-ground.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 186 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 16,127 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00186 $0.16127
Opus 5 $0.00093 $0.08063
Sonnet 5 $0.00037 $0.03225
Haiku 4.5 $0.00019 $0.01613

Measured 3d ago against content hash e5e568d74849, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

brd-ground 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.

plugins/dev-workflows/commands/brd-ground.md · 825 lines

How it starts

The opening of the file, as written. The whole thing — 825 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ground the BRD's requirement inventory against code and design: $ARGUMENTS

/brd-ground is the second command of the BRD-to-PRD flow (PA phase) — it takes the [BR#n] inventory /brd-intake wrote and checks its premises against real code and real design assets, at pinned commits, rather than letting a plausible-sounding claim stand unverified. Every finding is independently re-derived by a different agent before it counts as evidence (${CLAUDE_PLUGIN_ROOT}/references/grounding-format.md §8) — this command's whole job is to make that discipline happen, not to ground anything itself.

Usage: /brd-ground <BRD-KEY> [--depends-on <BRD-KEY>…] [--derivation-matrix|--no-derivation-matrix] [--no-design] [--no-docs] [--rebaseline]

Runs at either of the two levels <BRD-KEY> can name (${CLAUDE_PLUGIN_ROOT}/references/addressing.md §3) — a BRD that owns its source document, or one of its slices — grounding only the requirements that BRD claims. Unlike /brd-split, this command refuses neither: a slice is ground exactly as its parent is.

Standing rule, stated in full at Phase 4.5 and binding on every phase: documentation is a lead and a divergence finding — it is NEVER evidence for a [CG#n]. No finding this run writes may cite a documentation page in its evidence, under any verdict. A document is a claim about behaviour, not the behaviour.


Phase 0 — Resolve inputs and gate on main

  1. <BRD-KEY> (mandatory). Parse the first non-flag token; validate with key-valid (${CLAUDE_PLUGIN_ROOT}/references/addressing.md §1). If absent or invalid, stop: BRD_GROUND_NEEDS_KEY: /brd-ground needs a BRD key (shape ^[A-Z][A-Z0-9_]*(-\d+)+$) — re-run '/dev-workflows:brd-ground <KEY>'.
  2. Flags. --depends-on <BRD-KEY> — repeatable, each consuming the next token; validate each with key-valid and drop (warn, do not stop the run) any that fail shape. --no-design — boolean, skips Phase 5's design-grounder step. --no-docs — boolean, turns documentation grounding off for this run (Phase 1 step 0, Phase 4.5). --rebaseline — boolean, see Phase 3. --derivation-matrix / --no-derivation-matrix — mutually exclusive; absent means "let Phase 8 decide the default".
  3. $SPECS_PATH (required). If unset, stop naming SPECS_PATH, per the Required path environment variable unset rule in ${CLAUDE_PLUGIN_ROOT}/references/escalation-rules.md:
    choices: ["Set SPECS_PATH (enter the path)", "Cancel"]
    
  4. Specs-repo preflight. Cite ${CLAUDE_PLUGIN_ROOT}/references/specs-repo-git.md and execute its specs-preflight entry point (§3) inline, before the gate below — require-on-main performs no fetch of its own (phase-handoff.md §3.2) and relies on this step's best-effort one, the same ordering /design Phase 0 uses and for the same reason. Prompt-free and silent when the specs repo is clean and on its default branch. If it returns specs_git: blocked (§3.3 G0), carry that flag for the whole run.
  5. Resolve the BRD folder. resolve-address <BRD-KEY> (addressing.md §3), which searches specifications/ and the levels below it that resolve-address searches (three, per addressing.md §3) — either level a <BRD-KEY> can name — a BRD folder directly under specifications/, or the PRD- folder of a slice inside it. Absent → stop, without asserting which command would create it: no folder exists, so no brd-link.md exists either, and nothing on disk says whether this key names a BRD with a source document or a slice of one. Naming /brd-intake unconditionally would be the wrong advice for half the cases, exactly as it is in step 6's absent branch below: BRD_GROUND_NOT_FOUND: no BRD folder found for <BRD-KEY> under $SPECS_PATH/specifications/ (both levels searched) — check the key. A BRD with a source document of its own is created by /dev-workflows:brd-intake <BRD-KEY> @<brd-file>; a slice is created by /dev-workflows:brd-split on its parent. Do not run /brd-intake on a slice; it has no source document of its own.
  6. Gate this BRD's own inventory and ledger on main. Execute require-on-main (phase-handoff.md §3) against the resolved BRD folder's coverage-ledger.md. Whichever command wrote that ledger wrote the inventory beside it in the same handoff commit (coverage-ledger-format.md §3's creator table), so its presence on origin/<default> implies brd/brd-inventory.md landed with it: for a BRD with a source document of its own, that was /brd-intake, and brd/brd-defect-log.md landed too; for a slice, it was /brd-split running on the parent, and there is no defect log to land — a slice reads the parent's (brd-format.md §2.1). Map the §3.7 return by stopped first: any stopping row → stop, naming the concrete branch/PR state it reports; pass → proceed; pass_amending → proceed, printing the §3.3 row-B message; unmanaged → proceed as before this feature.

Read the full file on GitHub · 825 lines

Changes

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.

  1. 3d ago Changed · +56 lines e5e568d74849
  2. 8d ago First seen · 769 lines · 186 tokens per session scan A c05886d74711

Subscribe to this mod's changes

brd-ground is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 6d ago), licensed MIT. It adds 186 tokens to every session and 16,127 once invoked, about $0.0009 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.