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 2ykwang/agent-skills --skill decision-boardgit clone --depth 1 https://github.com/2ykwang/agent-skillsWrote 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/2ykwang/agent-skills/decision-board)<a href="https://agentmods.dev/skills/2ykwang/agent-skills/decision-board"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/decision-board/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/skills/2ykwang/agent-skills/decision-board"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/decision-board.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 | $0.00061 | $0.02309 |
| Opus 5.5 | $0.00024 | $0.00924 |
| Sonnet 5.5 | $0.00012 | $0.00462 |
| Haiku 4.5 | $0.00006 | $0.00231 |
Grade A, and why
decision-board 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 2mo 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Board
Render a single-file HTML board from a JSON spec, wait for the user to pick, read the result. Then apply the picks — write the doc, file the PRs, update configs, whatever the choices imply.
This skill only handles the picking step. Extracting decisions and judging trade-offs happens before; applying choices happens after.
When to use this skill
The trigger is structural fit, not domain and not count. In order of importance:
- Same option shape across items. Every item is
one-of-Nover options that share fields (label, optional cost / preview). If each item needs a custom shape, prose is better. - Preview is worth seeing. The user benefits from looking at each option's preview side-by-side rather than reading prose. If a single sentence captures the choice, inline Q&A is faster.
- One person, one sitting. Solo decision-making, not async review.
Item count is the weakest signal — roughly 5–30 is the typical sweet spot, but a well-structured 4-item case can still earn the board while a 10-item bag of unrelated questions doesn't. Fit beats count.
If the structural fit doesn't hold, push back and suggest a different format.
Workflow
The skill processes a session in five steps. Each step has a clear handoff — the agent owns 1, 2, 4, 5; the user owns 3.
1. Extract decisions from the user's material
The user usually arrives with unstructured material — a meeting recap, an audit document with conflicting paragraphs, a chat thread, a list in their head. Pull each decision out as a unit with four pieces:
- What is being decided (one-line title).
- The current state or conflict — actual code, the quoted paragraphs, the existing behavior. This becomes the decision's
context. - The candidate options — at least two, each with a short label and what changes if it's picked. This becomes
options[].label+options[].preview. - What you'd recommend and why — if the agent has an opinion, mark one option
recommendedand put the reasoning inrationale.
What ships with it
6 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.
- 2mo ago First seen · 166 lines · 61 tokens per session scan A 614cd4be0092
decision-board is a skill published in the GitHub repository 2ykwang/agent-skills (19 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 2,309 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 skills, from other repositories
resolve-plugins
Curate Claude Code skill / MCP / hook picks against live upstream sources and pin them in .claude/settings.json. Adding a process harness (a paired skill set) is an ordinary pick this door handles. Reads stack from docs/techstack.md, workflow signal from docs/overview.md + existing pins, then live-queries six source…
analytics-product
Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.
antigravity-workflows
Use when asked to ship a SaaS MVP, audit application security, build an AI agent, run browser QA, or design a domain model with multiple skills and verified checkpoints.
hermes-diagnostic-review
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls, and repeated fixes, then propose suggestion-only improvements and reusable skills. Human-gated; never auto-applies.
loop-designer
Compile a goal into a durable, file-backed agent loop — a .loop/ / charter any coding agent (Claude Code, Codex, Gemini, Grok) can execute unattended. Use when the user wants to "build a loop", "design a loop", "run X continuously/24-7", "make an agent keep working on Y", automate recurring work, or convert a big…
dev-environment-bootstrapping
Use this skill when the user asks to bootstrap, set up, create, or initialize a Shopware development environment from scratch — phrases like "set up a Shopware dev environment", "clone and install Shopware", "initialize a Shopware plugin project", "bootstrap Shopware and a new plugin called X", "get a fresh Shopware…