authoring-box-policy SKILL.md skillA

authoring-box-policy from strands-agents/box is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add strands-agents/box/authoring-box-policy@git:20261102.bcf4273

Pins git:20261102.bcf4273 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
strands-agents/box
Path
.agents/skills/authoring-box-policy/SKILL.md
Versions recorded
4
Latest version
git:20261102.bcf4273, committed Nov 2, 2026
First version recorded
Oct 7, 2026
Size
22,276 bytes
Repository stars
548
License
Apache-2.0

Author or edit a Strands Box policy (`policy.dw`) — turn an operator's natural-language allow/deny intent into a validated Dogwood policy over the box's fixed action vocabulary, including `when temporal { … }` history rules. Use when writing, editing, reviewing, or converting an intent into a box policy. This skill CREATES or EDITS a policy against the box's built-in schema — you never author a Dogwood schema, because the box ships a fixed one.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Authoring a Strands Box policy (Dogwood)

Your job: turn a natural-language authorization intent into a **Dogwood `policy.dw`** for a Strands
Box that loads clean and means what the operator actually intended. This is a *formalization* task
— the hard part is not the syntax (that is documented; see [Ground truth](#the-ground-truth-read-before-authoring))
but **pinning down ambiguous intent** and mapping it onto the right construct over the box's fixed
vocabulary.

**This is an interactive session, not a one-shot generator.** You work with the operator: draw out
the intent, ask a sharp question rather than guess when a requirement is underspecified, propose
rules, and confirm what stays refused. Do **not** return a policy you have not loaded.

**You author rules, not a schema.** A generic Dogwood deployment makes the operator author an action
schema and a service schema. Strands Box does not — the box ships a fixed, built-in schema, so the
vocabulary of actions, the one principal, and the context shape are already set. You write the
`permit` and `forbid` rules against that schema — [the fixed vocabulary](#the-fixed-vocabulary) is
below.

Follow the loop in order:
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_cum2tjm6rwnzrxk6/701cba404310374d7fb791a3f817de7469b021f4c9ed177d7d75033c0ad21663.json

Then /plugin install authoring-box-policy@markdownregistry-cum2tjm6rwnzrxk6 in Claude Code. It installs git:20261102.bcf4273, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add strands-agents/box/authoring-box-policy@sha256:701cba404310374d

The line at the top of this page pins the label git:20261102.bcf4273, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_cum2tjm6rwnzrxk6.svg)](https://markdownregistry.com/a/art_cum2tjm6rwnzrxk6)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in strands-agents/box/authoring-box-policy since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of authoring-box-policy from somewhere else? Ask it: where did my authoring-box-policy come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 4 versions of this file, between Oct 7, 2026 and Nov 2, 2026, about one every 9 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261102.bcf4273 latest2026-11-02 bcf4273 22,276 BA view · diff
git:20261029.bb05c962026-10-29 bb05c96 22,151 BA view · diff
git:20261026.37ff0542026-10-26 37ff054 22,062 BA view · diff
git:20261007.158dade2026-10-07 158dade 21,903 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (22276 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

strands-agents/box · 548 stars · license Apache-2.0 · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cum2tjm6rwnzrxk6
GET https://markdownregistry.com/api/v1/resolve?ref=strands-agents/box/authoring-box-policy
GET https://markdownregistry.com/api/v1/blob/701cba404310374d7fb791a3f817de7469b021f4c9ed177d7d75033c0ad21663

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from strands-agents/box

debug-os-failure-on-github SKILL.md skill
strands-agents/box · .agents/skills/debug-os-failure-on-github/SKILL.md · Debug a CI failure on an OS you are not on (you are on Linux, it fails on macos-latest, or the reverse) without opening…
git:20261007.158dade · audit A · 548 stars
docs-audit SKILL.md skill
strands-agents/box · .agents/skills/docs-audit/SKILL.md · Assess an existing Box documentation page (docs/user/, docs/design/, or a crate README.md) for accuracy against the…
git:20261007.158dade · audit A · 548 stars
docs-planner SKILL.md skill
strands-agents/box · .agents/skills/docs-planner/SKILL.md · Find the gaps in the Box documentation and produce a prioritized backlog for docs/user/ and docs/design/. Use when…
git:20261007.158dade · audit A · 548 stars
docs-reviewer SKILL.md skill
strands-agents/box · .agents/skills/docs-reviewer/SKILL.md · Review Box drafts in docs/user/ or docs/design/, and wording-only rewrites in docs/dev/. Use after docs-writer, before…
git:20261106.6bd1b2f · audit A · 548 stars
docs-sync SKILL.md skill
strands-agents/box · .agents/skills/docs-sync/SKILL.md · Find each Box doc that a change makes wrong or incomplete, and report the page to update in the same commit. Read-only…
git:20261026.bc94b4e · audit A · 548 stars
docs-writer SKILL.md skill
strands-agents/box · .agents/skills/docs-writer/SKILL.md · Draft or rewrite a Box page in docs/user/, docs/design/, or a crate README. Also use for wording-only rewrites in…
git:20261106.6bd1b2f · audit A · 548 stars
explore SKILL.md skill
strands-agents/box · .agents/skills/explore/SKILL.md · Launch a deep, multi-faceted investigation of a topic using parallel sub-agents. Each agent tackles a different angle…
git:20261007.158dade · audit A · 548 stars
kd SKILL.md skill
strands-agents/box · .agents/skills/kd/SKILL.md · Deep-dive a SINGLE key decision. Frame the question, weigh the candidate options honestly, and land a defensible answer…
git:20261007.158dade · audit A · 548 stars
setting-up-a-box SKILL.md skill
strands-agents/box · .agents/skills/setting-up-a-box/SKILL.md · Walk an operator through running an agent in a Strands Box for the first time, by following the getting started guide…
git:20261007.158dade · audit A · 548 stars
spec SKILL.md skill
strands-agents/box · .agents/skills/spec/SKILL.md · Walk through spec-driven development, design then requirements, producing a local .spec.md and .requirements.md for one…
git:20261007.158dade · audit A · 548 stars
AGENTS.md AGENTS.md file
strands-agents/box · AGENTS.md
git:20261113.7728614 · audit A · 548 stars
CLAUDE.md CLAUDE.md file
strands-agents/box · CLAUDE.md
git:20261007.158dade · audit B · 548 stars

Every file in strands-agents/box

Browse by kind, by grade A, or by owner.

Kept in .agents/skills, the folder Codex reads. More agent skills for Codex.