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 rjwalters/kicad-tools --skill repo-decidegit clone --depth 1 https://github.com/rjwalters/kicad-toolsWrote 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/rjwalters/kicad-tools/repo-decide)<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-decide"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-decide/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/rjwalters/kicad-tools/repo-decide"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-decide.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 | $0.00029 | $0.01462 |
| Opus 5.5 | $0.00012 | $0.00585 |
| Sonnet 5.5 | $0.00006 | $0.00292 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
repo-decide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex form of the
/repo:decidecommand. Other commands appear as$repo-<verb>skills. Helper scripts and.claude/paths below are relative to the repository root and exist when the Claude Code surface is installed alongside this one.
$repo-decide — Ranked Operator Decisions
When work is blocked on a decision that belongs to the operator (cost, an access grant, a policy change, something irreversible, a call about another person's system), don't ask an open question and don't bury the choice in a paragraph. Lay out the options best to worst, mark the one you recommend, and give the reason each option ranks where it does. Then the operator can answer "Q1: 1, Q2: 3" instead of re-deriving the tradeoffs you already worked out.
This command only drafts the questions. It does not decide anything. Presenting the draft in the session needs no confirmation. Posting it anywhere else (a chat room, an issue, a PR) is outward-facing and follows the same confirm-first rule as [[followups]], unless the user's own invocation already said where to post.
Usage
$repo-decide # Draft ranked questions for the decisions this session is blocked on
$repo-decide "<topic>" # Draft for one named decision
$repo-decide --post # Draft, confirm, then post where this project routes operator questions
Steps
1. Collect only real operator decisions
Go through the session (and the issue or PR at hand) for choices that are genuinely the operator's. Leave out anything you can settle from the code, the docs, or a sensible default. Settle those yourself and say so in one line. A decision belongs to the operator when it involves:
- money or a standing cost;
- granting, widening, or minting a credential or access;
- changing a written policy or making an exception to it;
- an irreversible or outward-facing action (publishing, deleting, migrating);
- a system, account, or budget someone else owns.
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.
- 2d ago Changed · +5 lines 52cbfd79ef39
- 8d ago First seen · 123 lines · 29 tokens per session scan A 0eb4eeb3955b
repo-decide is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,462 once invoked, about $0.0001 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 2026-11-01.
repo-decide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-deciderjwalters/kicad-tools | Skill | 73 | yesterday | MIT | A | 29 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |