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 skills/gastownhall/beads/beads-docsnpx skills add gastownhall/beads --skill beads-docsgit clone --depth 1 https://github.com/gastownhall/beadsWhat 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 | $0.00170 | $0.03266 |
| Opus 5 | $0.00085 | $0.01633 |
| Sonnet 5 | $0.00034 | $0.00653 |
| Haiku 4.5 | $0.00017 | $0.00327 |
Grade A, and why
beads-docs 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing beads docs
This is the house style for docs/ — the beads user documentation, published
as a Mintlify site. The goal is docs that motivate before they jargon, say the
same thing the same way everywhere, show concepts as pictures and snippets
instead of walls of prose, and never drift from the code. Apply it to any page
you create, edit, or review.
The audience of docs/ is a user of beads — a human or agent installing
bd, tracking work, and syncing it. Contributor-facing material lives in
engdocs/ and AGENTS.md and follows different rules (it may describe the
implementation literally). When this skill says "the docs," it means docs/.
1. The canonical model
Beads is a dependency-aware issue graph with a workflow layer on top. Teach it
consistently and link to the canonical concept page —
docs/core-concepts/index.md — rather than re-explaining it.
| Concept | Role | Key idea |
|---|---|---|
| bead (issue) | the unit of work | one tracked item with a hash ID (bd-a1b2), type, status, priority; "bead" and "issue" name the same thing |
| dependency | ordering | blocks edges hide a bead from agents until its blockers close; parent-child, related, discovered-from organize without blocking |
| ready work | what bd ready computes |
open beads with no open blockers, excluding in_progress, blocked, deferred, and hooked — the claimable frontier |
| formula | workflow source | a TOML/JSON file defining a DAG of steps; bd cook compiles it into a proto |
| proto | workflow template | a template epic (label template) with {{variables}}; not live work |
| molecule | instantiated workflow | real beads poured from a proto (bd mol pour); persistent |
| wisp | ephemeral molecule | same instantiation, transient lifecycle (bd mol wisp); purged by bd purge |
| gate | async wait | blocks a workflow step until closed — by a human, a timer, a GitHub run/PR, or a cross-rig bead |
| sync | cross-machine movement | Dolt push/pull over refs/dolt/data on the git remote; .beads/issues.jsonl is a passive export, never the database |
| federation | cross-repo sync | peer-to-peer sharing of beads across repos/organizations |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 223 lines · 170 tokens per session scan A fe88cbe992cb
beads-docs is a skill published in the GitHub repository gastownhall/beads (26,754 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session and 3,266 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 2026-08-30.
Other skills, from other repositories
skill-creator
Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.
find-me-skills
Find Agent Skills for a goal the user cannot name yet, then export an installable bundle. Use when they ask which skills fit a project. Don't use for installing named skills, authoring skills, or catalog maintenance.
skill-upstream-pr
Improve an open-source GitHub skill and open a friendly suggestion PR upstream: fork, run skill-auto-improver, attach asm eval before/after metrics. Don't use for local-only skills, authoring from scratch, bulk repos, or registry publish.
well-formed
Review pull request diffs for code smells, style issues, and safety problems before merging.
skill-auto-improver
Improve an external, legacy, or drifted SKILL.md to the skill-creator standard — hard validation gates plus an advisory predictability audit. Don't use for authoring from scratch (skill-creator output is already standard), bulk eval, or prose edits.
skill-index-updater
Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for authoring (skill-creator), improving (skill-auto-improver), or install (asm install).