bd-to-br-migration
An agent skill by Dicklesworthstone, from Dicklesworthstone/beads_rust. Tags: cli, documents, local-workflow, migration, version-control.
What it does
Migrate docs from bd (beads) to br (beads_rust). Use when updating AGENTS.md, converting bd commands, "bd sync" → "br sync --flush-only", or beads migration.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add Dicklesworthstone/beads_rust --skill bd-to-br-migrationOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/Dicklesworthstone/beads_rust
cp -r beads_rust/skills/bd-to-br-migration ~/.claude/skills/bd-to-br-migrationSafety box score
Grade B, low risk: 18 of 100 risk points, rated 2026-09-25. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a documentation migration tool that rewrites bd/beads references to br/beads_rust and includes scripts for discovery and verification. Its main blast radius is bulk Markdown edits across many AGENTS.md files, plus examples that normalize git commit/push and message-sending workflows; it does not handle secrets or privileged system settings.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | The shipped helpers are Bash scripts (`scripts/find-bd-refs.sh`, `scripts/verify-migration.sh`) that run `grep` and shell loops such as `for f in /data/projects/*/AGENTS.md; do`, so it can execute shell commands, but only simple read-only checks. |
| Network access | 0 (none) | No script downloads files or calls remote APIs; there is no `curl`, `wget`, or HTTP client usage in the shipped files. |
| Filesystem reach | 2 (moderate) | The batch guidance targets many files at once (`/data/projects/*/AGENTS.md`) and even shows rollback with `git checkout -- /data/projects/*/AGENTS.md`, so the edit surface can span multiple projects. |
| Secrets & credentials | 0 (none) | Nothing reads token stores, `.env` files, browser sessions, keychains, or asks the user to paste credentials. |
| Privilege & persistence | 0 (none) | There is no `sudo`, global install, service registration, shell startup editing, or OS configuration change. |
| Instruction hijack surface | 0 (none) | The text is direct migration guidance; it does not ask the agent to ignore rules, hide actions, or follow untrusted remote instructions. |
| Irreversible actions | 2 (moderate) | `references/TRANSFORMS.md` includes operational examples with `git push` and `send_message(...)`, so following those patterns could publish changes or send messages on the user's behalf, even though they are documented examples rather than active code. |
| Transparency | 0 (none) | All shipped files are plain markdown or readable shell scripts; there are no binaries, packed payloads, or runtime-decoded code. |
Before installing
- Read `references/TRANSFORMS.md` and `references/BULK.md` to confirm you want docs that include `git push` and `send_message(...)` examples.
- Run `./scripts/verify-migration.sh` on a scratch Markdown file first to see the exact file checks it performs.
- If you may batch-edit many projects, confirm the intended scope of `/data/projects/*/AGENTS.md` before letting the agent run.
Rated 2026-09-25 by an automated review of 8 files from the skill's repository.
Source
- Repository
- Dicklesworthstone/beads_rust (all skills from this repository)
- Path
- skills/bd-to-br-migration/SKILL.md
- Branch
- main
- Updated
- 2026-09-23
Related skills
- filesystem-context — This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery.
- agents-get-started — Use when a developer wants to create a new agent project or get started with AgentCore.
- caveman — Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens".
- caveman-compress — Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
- caveman-stats — Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report.
- megacave — Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan.