yegge

yegge is an agent for Claude Code from DollarDill/beads-superpowers. It costs 39 tokens per session (1,343 once invoked), scanned A, original, MIT.

The main coordinating agent for a project. It receives each request, decides which skills should handle it, and coordinates research, planning, implementation, checking, and delivery for larger tasks.

In plain words
What is it for?
Use it to route quick questions, research requests, simple edits, and larger software changes to the appropriate project capabilities.
Why use it?
It provides one entry point for different kinds of work and helps keep multi-step requests organized from investigation through completion.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Part of the beads-superpowers plugin — 22 skills, 1 agent, 1 hook shipped together

Good fit Use it to route quick questions, research requests, simple edits, and larger software changes to the appropriate project capabilities.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dollardill/beads-superpowers/yegge
Install

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.

Clone the repo
git clone --depth 1 https://github.com/DollarDill/beads-superpowers

Made for: Claude Code.

Or install beads-superpowers, the plugin that ships this one along with the rest of its 22 skills, 1 agent, 1 hook.

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 yegge

README.md
[![agentmods](https://agentmods.dev/badge/agents/dollardill/beads-superpowers/yegge/github.svg)](https://agentmods.dev/agents/dollardill/beads-superpowers/yegge)
Your own site
<a href="https://agentmods.dev/agents/dollardill/beads-superpowers/yegge"><img src="https://agentmods.dev/badge/agents/dollardill/beads-superpowers/yegge/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 yegge

Your own site · 80×15
<a href="https://agentmods.dev/agents/dollardill/beads-superpowers/yegge"><img src="https://agentmods.dev/badge/agents/dollardill/beads-superpowers/yegge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,343 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 $0.00039 $0.01343
Opus 5 $0.00019 $0.00672
Sonnet 5 $0.00008 $0.00269
Haiku 4.5 $0.00004 $0.00134

Measured 9d ago against content hash 006244037ebf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

yegge 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 9d 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.

example-workflow/agents/yegge.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

yegge — Orchestrator Agent

Named after Steve Yegge, creator of Beads.

You are the primary agent for this session — all requests come through you. You triage each request and route it to the skills that do the work. For non-trivial work you coordinate the flow (research → plan → implement → verify → ship) and let each skill own its own detail and gates. Don't restate what the skills already contain.

Triage — route first

Triage is routing, not law: use judgment, and scale process to the task.

Request What to do Skills
Quick question ("what does X do?", "explain this error") Answer directly. No bead, no skill.
Simple change — ONLY: typo, comment, rename, or a single-file obvious fix with an obvious check Do it directly; bead optional; verify (show evidence); commit. No worktree / doc-audit / PR. If it doesn't fit this list, treat it as non-trivial. verification-before-completion
Non-trivial — a feature, refactor, 3+ steps, multi-file, or an architectural / production-impacting change Run the full flow below. see flow
Research query ("what is X?", "how does Y work?", "compare A vs B") Research, then write the findings to the knowledge base. research-driven-development

The full flow — non-trivial work

Each step invokes the skill that owns it; the skill carries its own detail, gates, and beads.

  1. Research the unknowns — Skill(beads-superpowers:research-driven-development) (skip if already well understood; pass the nested marker here — it's a sub-step, so findings return without the end-gate).
  2. Brainstorm the design — Skill(beads-superpowers:brainstorming) → spec + user approval gate.
  3. Plan it — Skill(beads-superpowers:writing-plans) → task plan + user approval gate.
  4. Implement in isolation — Skill(beads-superpowers:using-git-worktrees), then Skill(beads-superpowers:test-driven-development) (single task) or Skill(beads-superpowers:subagent-driven-development) (multi-task). Before merging sub-agent work: re-run the full suite yourself (don't trust the sub-agent's run), scan the diff for scope creep / debug artifacts, invoke Skill(beads-superpowers:requesting-code-review), and reject + re-delegate if any gate fails.
  5. VerifySkill(beads-superpowers:verification-before-completion). Evidence before any "done", on every path.
  6. DocumentSkill(beads-superpowers:document-release).
  7. FinishSkill(beads-superpowers:finishing-a-development-branch).

Read the full file on GitHub · 74 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. 9d ago First seen · 74 lines · 39 tokens per session scan A 006244037ebf

Subscribe to this mod's changes

yegge is an agent published in the GitHub repository DollarDill/beads-superpowers (26 stars, last pushed 17d ago), licensed MIT. It adds 39 tokens to every session and 1,343 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

arn-code-ux-specialist

This agent should be used when the user needs UI/UX design guidance for a feature, or when the arn-code-feature-spec-teams skill needs a UX specialist perspective during team debate. Specializes in component architecture, user experience flows, accessibility, and frontend patterns. Context: Invoked by…

AppsVortex/arness · 237 tokens

backend

Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.

restarter/lets-workflow · 39 tokens

database

Database expert for schema design review, migration analysis, query optimization, index assessment, and transaction safety. Use when reviewing database schemas, migrations, ORM code, or raw queries.

restarter/lets-workflow · 37 tokens

coverage-guardian

Use to verify and repair the coverage gate — run the repo's unit tests with coverage, find touched files below 95%, and write the specific missing tests to close the gaps. Language- and framework-agnostic.

theam/claude-dev-kit · 48 tokens

evidence-collector

Independent verification agent. Takes FINAL-PLAN.md and independently verifies every acceptance criterion was met. No access to executor output.

malakhov-dmitrii/forge · 29 tokens

secretary

Decide whether a question really needs the owner. Consult this agent BEFORE asking the owner anything - it answers from the vault's decision policy and either settles the question (DECIDE) or tells you to escalate (ESCALATE). Read-only; it judges, it never acts.

atman-33/workhub · 59 tokens