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 katalalab/katala-os --skill goal-contractgit clone --depth 1 https://github.com/katalalab/katala-osWrote 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/katalalab/katala-os/goal-contract)<a href="https://agentmods.dev/skills/katalalab/katala-os/goal-contract"><img src="https://agentmods.dev/badge/skills/katalalab/katala-os/goal-contract/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/katalalab/katala-os/goal-contract"><img src="https://agentmods.dev/badge/skills/katalalab/katala-os/goal-contract.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 | $0.00092 | $0.00785 |
| Opus 5 | $0.00046 | $0.00392 |
| Sonnet 5 | $0.00018 | $0.00157 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
goal-contract 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 10d 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.
What it actually says
goal-contract — bounded execution for open-ended goals
Prevents a common failure mode: open-ended goal sessions that run for dozens of turns, burning context on auto-compactions, until the operator has to interrupt and ask for completion criteria.
When to use
/goalで何かを依頼されたとき（内容を問わず毎回）- 「環境をブラッシュアップして」「最高の設定にして」「全部進めて」「走り切って」など、終了条件が自明でない依頼
- WARN/エラーの全解消系（「全て解消して」— "全て"の母集団を先に固定する必要がある）
Do not use for:
- 単発の具体的コマンド実行や1ファイル修正（終了条件が自明）
- 質問への回答だけのターン
Procedure
- 解釈 (1 line). Restate the goal concretely, naming referents（URL、PR番号、対象マシン、対象ディレクトリ）.
- 完了条件 (3–5 checks). Each must be verifiable by a real command or observable state — not "十分に改善した". Examples: 「
verify.shが PASS」「WARN 母集団 N 件のうち解消可能な M 件が 0 件」「PR #X のレビューコメント全件に対応コミットあり」. - スコープ外 (1–2 lines). What this session will NOT do（例: リモートノードへの書き込み、依存追加、baseline編集）.
- Announce the block, then run. Do not wait for approval. The operator grants latitude by default; the contract exists so both sides know when it ends.
- Checkpoints. Every major phase, ≤3 lines: 完了 / 進行中 / 残り + 完了条件 x/y.
- Terminate. When all criteria pass (or remaining ones are blocked by something only the operator can decide), write the final report and END the goal. Do not invent new work. If genuinely useful follow-ups surfaced, list ≤3 as 次アクション候補 instead of doing them.
Unbounded goals
「人生を最高に」「議論しながらブラッシュアップ」のような無限ゴールは、有限バッチに変換して宣言する:
解釈: 無限ゴールのため今回は有限バッチ化 — 影響の大きい改善 上位5件を実施。 完了条件: 5件それぞれに 適用+検証コマンド結果 が揃うこと。
Then recommend /new for the next batch — goal text is re-injected every turn, so one eternal session wastes context that fresh sessions don't.
Report format (turn-final)
- 結論（達成 x/y と一言）
- 証拠（コマンド+結果、パス）
- 検証済み / 未検証 の区別
- 次アクション候補（≤3、実行はしない）
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.
- 10d ago First seen · 45 lines · 92 tokens per session scan A cb9264f52545
goal-contract is a skill published in the GitHub repository katalalab/katala-os (2 stars, last pushed 11d ago), licensed MIT. It adds 92 tokens to every session and 785 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…