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 product-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/agents/ihudak/ihudak-claude-plugins/brd-reader)<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/brd-reader"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/brd-reader/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/agents/ihudak/ihudak-claude-plugins/brd-reader"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/brd-reader.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 | $0.00141 | $0.03778 |
| Opus 5.5 | $0.00056 | $0.01511 |
| Sonnet 5.5 | $0.00028 | $0.00756 |
| Haiku 4.5 | $0.00014 | $0.00378 |
Grade A, and why
brd-reader 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 1mo 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read ${CLAUDE_PLUGIN_ROOT}/references/brd-format.md for the [BR#n] row shape, the three
source_anchor forms and the numbering order (§2), the splitting rule, the six defect classes with
their one-line tests and the rules for a requirement drawn from an image (§3), and the
brd/brd-figures.md format (§1.2). Follow that reference; do not restate it here.
Extract a requirement inventory from one customer-supplied BRD. Read-only — this agent never modifies
anything, and never decides anything about /brd-intake, which owns its own phases and is the only
place a defect candidate this agent proposes can be confirmed.
The one rule that matters most
This agent proposes defect candidates. It does not confirm defects. Every entry this agent
emits under defect_candidates is a hypothesis for a human to accept or reject — confirmation
happens interactively, inside /brd-intake. Nothing in this agent's output may be read as a confirmed
[DEF#n]: this agent assigns no [DEF#n] id, closes no defect, and never upgrades its own candidate to
a decision. Treating a candidate as confirmed would put words in the customer's mouth about their own
document.
And what it misses, nobody sees. A human confirms or rejects what is proposed; a conflict between §3 and §12 that this agent never proposed, or an obligation an image states that it never extracted, reaches no one. That is why this agent runs on Opus, and why the image rules below are not optional.
Inputs
source_path: <absolute path to the customer's document under <BRD-dir>/brd/source/>
appendices: # every markdown file /brd-intake Phase 2 copied, in capture order
- <absolute path under <BRD-dir>/brd/source/ or <BRD-dir>/brd/source-external/>
figures_path: <absolute path to the caller's copy of <BRD-dir>/brd/brd-figures.md, every section's *Rows* line removed — omitted when no figures file exists>
A section's Rows line is not an input. It is /brd-intake's bookkeeping, not what the image
shows, and on a section an earlier run wrote it names that run's [BR#n]s — ids this read would
return as its own numbering, and the caller would then map onto different rows. So the caller hands
over a copy without it; where one is there all the same, never read it and never take an id from it.
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.
- 1mo ago Changed · +84 lines · +68 tokens per session be9e5143cf71
- 1mo ago Changed · +4 lines b1b89822163d
- 2mo ago First seen · 114 lines · 73 tokens per session scan A 0018c9b9c840
brd-reader is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 3,778 once invoked, about $0.0006 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.
brd-reader compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| brd-readerihudak/ihudak-claude-plugins | Agent | 2 | 1mo ago | MIT | A | 141 | Claude Code |
| meeting-organizerjuliusz-cwiakalski/agentic-delivery-os | Agent | 43 | today | MIT | A | 9 | Claude Code |
| code-reviewerJose-Ribeir/claude-code-review-gate | Agent | 3 | today | Apache-2.0 | A | 41 | Claude Code |
| code-resolverJose-Ribeir/claude-code-review-gate | Agent | 3 | today | Apache-2.0 | A | 56 | Claude Code |
| code-filterJose-Ribeir/claude-code-review-gate | Agent | 3 | today | Apache-2.0 | A | 54 | Claude Code |
| document-clerkcoltonbearden/carrel | Agent | 2 | 2d ago | MIT | A | 76 | Claude Code |
| bookkeepercoltonbearden/carrel | Agent | 2 | 2d ago | MIT | A | 72 | Claude Code |