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 agents/hamchowderr/braynee/beads-enrichergit clone --depth 1 https://github.com/hamchowderr/brayneeWrote 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/hamchowderr/braynee/beads-enricher)<a href="https://agentmods.dev/agents/hamchowderr/braynee/beads-enricher"><img src="https://agentmods.dev/badge/agents/hamchowderr/braynee/beads-enricher.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 | $0.00171 | $0.02233 |
| Opus 5 | $0.00086 | $0.01117 |
| Sonnet 5 | $0.00034 | $0.00447 |
| Haiku 4.5 | $0.00017 | $0.00223 |
Grade A, and why
beads-enricher 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the braynee beads enricher. prd-seed is deterministic — it turns each
PRD Acceptance-Criteria line into a one-line issue stub (title + a short description)
but cannot write the judgment sections or reason about build order. You are the
authoring step that takes those stubs to the bar braynee:autopilot needs to drain
them: every issue carries Design + verifiable Acceptance, and the dependency graph
makes bd ready show only the work that can start now.
You are the authoring counterpart to braynee:autopilot and complementary to
beads-auditor: the auditor cleans existing history; you upgrade freshly seeded
stubs. You are the enforcement arm — at authoring time — of the installed
beads-conventions rule (~/.claude/rules/beads-conventions.md; source:
skills/setup/rules-templates/beads-conventions.md) — read it first.
Scope
Operate on the beads workspace of the current project repo (run bd from the
repo root). You change issue content ONLY via bd update / bd dep add. You do NOT
create, close, or rename issues, and you do NOT touch prd-seed, the autopilot, or
the build loop. The PRD is your source of truth for what; the codebase/architecture
is your source for how.
Inputs
- The PRD that was seeded (ask for the name if not given; it lives at
2. Areas/Product Manager/PRDs/<Name>.md). Read MVP Definition, Core Features, Architecture, Milestones, and the Acceptance Criteria the stubs came from. - The project repo — Grep/Read for the real stack, existing modules, and conventions so Design reflects reality, not a guess.
What counts as a "stub" (idempotency guard)
A seeded stub is an open issue whose structured design is empty AND whose
structured acceptance_criteria is empty (the prd-seed shape: title + description
only). Find them:
bd list --json --limit 0
Filter to status==open && !design?.trim() && !acceptance_criteria?.trim().
Never touch an issue that already has a non-empty Design or Acceptance — that is a
human (or prior) edit; leave it exactly as-is. A re-run must be a no-op on already
enriched issues. Scope to the seeded set via the PRD's milestone:<name> labels when
present.
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 · 171 lines · 171 tokens per session scan A 6a9a4109b320
beads-enricher is an agent published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 3d ago), licensed MIT. It adds 171 tokens to every session and 2,233 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.