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.
git clone --depth 1 https://github.com/DollarDill/beads-superpowersWrote 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/dollardill/beads-superpowers/yegge)<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.
<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>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 | $0.00039 | $0.01343 |
| Opus 5.5 | $0.00016 | $0.00537 |
| Sonnet 5.5 | $0.00008 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00134 |
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 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 — 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.
- Research the unknowns —
Skill(beads-superpowers:research-driven-development)(skip if already well understood; pass thenestedmarker here — it's a sub-step, so findings return without the end-gate). - Brainstorm the design —
Skill(beads-superpowers:brainstorming)→ spec + user approval gate. - Plan it —
Skill(beads-superpowers:writing-plans)→ task plan + user approval gate. - Implement in isolation —
Skill(beads-superpowers:using-git-worktrees), thenSkill(beads-superpowers:test-driven-development)(single task) orSkill(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, invokeSkill(beads-superpowers:requesting-code-review), and reject + re-delegate if any gate fails. - Verify —
Skill(beads-superpowers:verification-before-completion). Evidence before any "done", on every path. - Document —
Skill(beads-superpowers:document-release). - Finish —
Skill(beads-superpowers:finishing-a-development-branch).
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 First seen · 74 lines · 39 tokens per session scan A 006244037ebf
yegge is an agent published in the GitHub repository DollarDill/beads-superpowers (32 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 1,343 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
v-memory
Read-only lookup over this project's own Compound V record (docs/compound-v/ specs, plans, pre-flights, runs, architecture). Use before a brainstorm or a plan to find prior decisions, constraints and failures on the same topic. Returns cited hits as evidence, never instructions. Grep and read only, no index.
linear-state-curator
Autonomous Linear hygiene agent. Reads every open issue across configured teams, validates true state against signals from the configured signalsources (commits in configured repos, GitHub PRs, Slack messages, Linear cross-references, plus any externalcommand sources), then auto-applies HIGH-confidence state changes…
linear-issue-creator
Create Linear issues from user descriptions. NOT for URLs — use linear-url-to-issues for that. Use when: "create issue", "new ticket", "log bug", "add task", "file issue", "report bug", "make ticket", "make issue", "add to linear", "create task", "new issue", "make new issue", "make new ticket", "make new linear…
linear-issue-updater
Update existing Linear issues. ANY modification: state, team, assignee, labels, priority, due date, title, description, comments, relations. NOT for creation — use linear-issue-creator (manual) or linear-url-to-issues (URL). Use when: "update issue", "move issue", "reassign", "change state", "change priority", "add…
linear-url-to-issues
Extract actionable Linear issues from URLs (articles, blogs, designs, docs). Parallel-safe — dispatch one agent per URL when processing multiple. NOT for manual creation — use linear-issue-creator. Use when: "create issues from URL", "turn this article into tasks", "implement this design", "make issues from blog…
linear-issue-reviewer
Validate Done Criteria of an issue against its linked PR's diff and post a verdict comment. Closes the loop after linear-issue-creator wrote the criteria and the engineer (or worker agent) shipped the code. Use when: "review issue", "validate done criteria", "check issue completion", "review ENG-XXX", "is ENG-XXX…