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 skills add dcosson/h2 --skill plan-to-beadsgit clone --depth 1 https://github.com/dcosson/h2Wrote 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/skills/dcosson/h2/plan-to-beads)<a href="https://agentmods.dev/skills/dcosson/h2/plan-to-beads"><img src="https://agentmods.dev/badge/skills/dcosson/h2/plan-to-beads.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 67 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00037 | $0.03026 |
| Opus 5 | $0.00018 | $0.01513 |
| Sonnet 5 | $0.00007 | $0.00605 |
| Haiku 4.5 | $0.00004 | $0.00303 |
Grade A, and why
plan-to-beads 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 8d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan to Beads
Read reviewed plan docs and decompose them into implementation beads (epics + tasks) with correct dependencies and sizing. Designed for concierge/scheduler agents preparing implementation work after the planning cycle is complete.
Inputs
$0: Scope — one of:- A batch name (e.g.,
batch3) — decomposes all plan docs in that batch - A single plan doc identifier (e.g.,
02b-gateway) — decomposes one doc + its addenda all— decomposes the entire plan index
- A batch name (e.g.,
$1(optional):--dry-run— output proposed beads as markdown without creating them- Plans directory:
docs/plans/(or the project's established plans directory)
Critical Rules
- Do NOT create beads smaller than ~200 lines of implementation code. If a piece is too small, merge it with a related piece.
- Do NOT split unit/integration tests into separate beads from their implementation. Tests go in the same bead as the code they test.
- Do NOT auto-assign beads to agents. All beads are created unassigned — the concierge/scheduler assigns them.
- Do NOT create beads for plan docs that haven't completed their full review cycle including seam review. Check that docs are in "Seam Reviewed" status (not just "Approved") before proceeding. If seam review has completed but the Implementation Guide (
docs/plans/00-implementation-guide.md) does not yet exist, flag this to the orchestrator — the guide should be generated (Phase 4.75 in plan-orchestrate) before bead creation proceeds. - NEVER start implementation work when running this skill. This skill creates beads only. The scheduler/concierge kicks off implementation as a separate step after reviewing and confirming the bead structure.
- External/acceptance test beads must include "tests pass against a running system" as acceptance criteria, not just "test files written". The bead is not done until the tests actually execute and pass.
Phase 1: Read & Catalog
- Read
docs/plans/00-plan-index.mdfor:- Batch structure and which docs are in scope
- Cross-doc dependency graph
- Status of each doc (must be "Plan complete" or have clean review)
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.
- 8d ago First seen · 261 lines · 37 tokens per session scan A c074b0f85c79
plan-to-beads is a skill published in the GitHub repository dcosson/h2 (159 stars, last pushed 12d ago), licensed MIT. It adds 37 tokens to every session and 3,026 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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.