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.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install dev-workflowsWrote 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/ihudak/ihudak-claude-plugins/brd-package)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/brd-package"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/brd-package.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 | $0.00236 | $0.17181 |
| Opus 5 | $0.00118 | $0.08590 |
| Sonnet 5 | $0.00047 | $0.03436 |
| Haiku 4.5 | $0.00024 | $0.01718 |
Grade A, and why
brd-package 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 yesterday.
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 — 927 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn the decided BRD into a package a customer can actually review: $ARGUMENTS
/brd-package is the fifth command of the BRD-to-PRD flow (PM phase) — it takes the register
/brd-interview wrote and the [C] questions it held, attacks the package before the customer
does, and renders a bundle for a reviewer with a vanilla agent and nothing installed. Its whole
discipline is one rule: everything this command emits is read by somebody outside the delivery
organisation who cannot ask what a path means
(${CLAUDE_PLUGIN_ROOT}/references/bundle-packaging.md §1, D12). This command exists to make that
happen, not to restate it.
Usage: /brd-package <BRD-KEY> [--depends-on <BRD-KEY>…]
Runs at either of the two levels <BRD-KEY> can name
(${CLAUDE_PLUGIN_ROOT}/references/addressing.md §6) — a BRD that owns its source document, or
one of its slices. It refuses neither and behaves identically at both: a slice holds its own
register, its own [C] question set and its own findings, and it is packaged from those and no
others. The bundle this run builds is the bundle of the BRD it was given.
Standing rule, binding on every phase below. Nothing that names this plugin, this repository or
this harness may appear in the rendered prompt, the delivery note, or any document inside the
bundle. Not a path rooted at the plugin's install directory, not a references/… citation, not a
slash command, not an agent or skill name, not a § section reference
(${CLAUDE_PLUGIN_ROOT}/references/customer-review-schema.md §1). The section How nothing
plugin-internal reaches the customer below states the ordering and the scan that make that
structural rather than aspirational.
This command takes no --no-docs, and it does no documentation grounding at all. That is a
decision, not an omission. /brd-intake and /brd-ground already ground this BRD against the
shipped product documentation when $DOCS_PATH resolves (D22,
${CLAUDE_PLUGIN_ROOT}/references/docs-grounding.md), and /brd-interview deliberately does none
for the same reason this command does none: it works on decisions already taken. This command
goes one step further — it establishes no claim of its own at all. It renders what other commands
recorded, and a documentation page cannot change a decision that is already in the register or a
finding that is already verified; consulting one here could only introduce an ungrounded sentence
into a bundle whose whole value is that every sentence in it is traceable. So there is no flag to
turn off, no resolve-docs-grounding call, and no docs grounding: line in this command's report.
The sentence is written here because leaving it unwritten is exactly how the gap it forecloses gets
shipped.
No repository is opened, at any point. Every commit this package cites was pinned and proven
clean by /brd-ground, and the repo→SHA table is read from that run's grounding/baselines.md. So
there is no baseline gate here, no dirty-tree stop, and no $REPOS_PATH requirement. The three
baseline-integrity commands are not re-run by this command — they are handed to the customer's
reviewer, written out with the repository and the commit substituted, so the customer re-derives
the pin against their own checkout rather than taking the package's word for it
(${CLAUDE_PLUGIN_ROOT}/references/grounding-format.md §4).
How nothing plugin-internal reaches the customer
Five properties, and every one of them is a property of the order and the inputs of the phases below, not an instruction to be careful. Together they are the guarantee; individually none of them is.
- The schema is rendered from its own file, from the boundary that file declares, and never in
full.
customer-review-schema.mdseparates a preamble addressed to the delivery team from a body addressed to the customer, and states where the boundary falls. The Render the customer prompt phase reads the boundary statement out of the file before it renders, and stops if it is no longer there. Rendering the whole file would put that file's ownreferences/…citations in front of a reader with no plugin — the exact failure D12 exists to prevent — and the citations are collected in the preamble precisely so that the boundary has something to protect.
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.
- yesterday Changed · +85 lines 6f7d19463c0b
- 6d ago First seen · 842 lines · 236 tokens per session scan A cbe49786a5ea
brd-package is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 236 tokens to every session and 17,181 once invoked, about $0.0012 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 commands, from other repositories
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
confluence-publish
Publicar documentación del proyecto en Confluence. Convierte markdown a formato Confluence y crea/actualiza páginas en el espacio del proyecto.
plan
Hierarchical planning entry point — all 11 plan verbs in one command. v3.7.2 consolidates /aura-frog:plan- (10 commands) into a single dispatcher that routes via the plan-orchestrator skill. The legacy plan- aliases still work as thin stubs.
plan-freeze
Manually freeze a plan node, cascading to descendants. Alias for /aura-frog:plan freeze (v3.7.2+).