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/mhashim6/kauri/record-decisionnpx skills add mhashim6/kauri --skill record-decisiongit clone --depth 1 https://github.com/mhashim6/kauriWrote 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/mhashim6/kauri/record-decision)<a href="https://agentmods.dev/skills/mhashim6/kauri/record-decision"><img src="https://agentmods.dev/badge/skills/mhashim6/kauri/record-decision.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00415 |
| Opus 5 | $0.00016 | $0.00208 |
| Sonnet 5 | $0.00006 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
record-decision scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Record a Decision
You are recording a project decision using Kauri. The decision should be a deliberate choice with rationale — not a trivial implementation detail.
Before recording
- Check the existing taxonomy: use
kauri_taxonomy_listto see available tags. - Check for existing related decisions: use
kauri_querywith a text search to avoid duplicates.
Recording the decision
Use kauri_record with:
- title: A short, scannable title (the user provided: "$ARGUMENTS")
- body: The full rationale in markdown. Include:
- What was decided
- Why this option was chosen over alternatives
- Any constraints or trade-offs involved
- tags: One or more tags from the taxonomy. If nothing fits, use
allow_new_tags: true. - files: Any file paths this decision relates to (optional but valuable for staleness detection).
- links: IDs of related decisions (optional — creates bidirectional "see also" links).
- source:
agent:claude-code - scope:
project(default). Useuseronly if the user explicitly asks for a personal/cross-project decision.
When NOT to record
- Trivial implementation details (variable names, formatting)
- Temporary workarounds intended to be removed immediately
- Facts or observations (decisions are choices, not notes)
After recording
Confirm the record was created and show the user the ID and title.
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.
- 3d ago First seen · 43 lines · 32 tokens per session scan A 432e8cab65f7
record-decision is a skill published in the GitHub repository mhashim6/kauri (5 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 415 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 2026-08-31.
Other skills, from other repositories
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
data_analysis
基于已确认数据执行可审计的数学计算和描述统计。.
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.