Kd

What it does

When your agent uses it

• You need to rigorously decide one thing
• Such as which X should we use
• Evaluate the tradeoffs of ...
• Make the call on ...

Example prompts

• “which X should we use”
• “should we do A or B”
• “evaluate the tradeoffs of ...”
• “/kd”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Check whether decisions.md already owns this question. Search it by topic, not by
2. 2Frame the question. State what must be decided and why it is hard. A question with an
3. 3Find the real options. Three to six, each one a thing someone would actually build.
4. 4Weigh them. Name the criteria that decide it, and say which option wins each. Where a
5. 5Write the draft to .agents/drafts/kd/{YYYY-MM-DD}-{slug}.md, in the
6. 6Report in chat: the one-line recommendation, its cost, and the draft's path. Then stop
7. 7Append the entry only when the user says it is decided. Set the draft's status to

What it can do on your machine

Read from SKILL.md and the folder at commit 2c874ea. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Kd loads about 1.3k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 654 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~103

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from strands-agents/box at commit 2c874ea, republished under its Apache-2.0 licence (© strands-agents). 654 words, ~1,321 tokens.

name

kd

description

Deep-dive a SINGLE key decision. Frame the question, weigh the candidate options honestly, and land a defensible answer in a local draft. Once the user decides it, append one entry to docs/design/decisions.md, or update the entry it re-answers. Use when you need to rigorously decide one thing, such as "which X should we use", "should we do A or B", "evaluate the tradeoffs of ...", or "make the call on ...".

# {The question}

**Status:** Proposed | Decided {YYYY-MM-DD}
**Owns or re-answers:** {new | decisions.md#{anchor}}

## Why this is hard
## Options
## Criteria, and which option wins each
## Evidence
## Recommendation, and its cost

<a id="{slug}"></a>
### {The answer, stated as a claim. Never a question.}

{Two to six sentences. What is now true, in the present tense, and what it lands in: the type,
the module, or the mechanism. The obvious alternative, and why it lost, in one sentence. What the
decision costs the reader: a limitation, a residual risk, or a thing they must not do.}

© strands-agents, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/kd of strands-agents/box.

Open the folder on GitHubat commit 2c874ea