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 voxpelli/claude-beads --skill vendor-syncgit clone --depth 1 https://github.com/voxpelli/claude-beadsWrote 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/voxpelli/claude-beads/vendor-sync)<a href="https://agentmods.dev/skills/voxpelli/claude-beads/vendor-sync"><img src="https://agentmods.dev/badge/skills/voxpelli/claude-beads/vendor-sync/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/voxpelli/claude-beads/vendor-sync"><img src="https://agentmods.dev/badge/skills/voxpelli/claude-beads/vendor-sync.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 | $0.00083 | $0.04215 |
| Opus 5 | $0.00042 | $0.02107 |
| Sonnet 5 | $0.00017 | $0.00843 |
| Haiku 4.5 | $0.00008 | $0.00421 |
Grade C, and why
vendor-sync scanned grade C with 1 finding 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 9d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf <prefix>/node_modules How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vendor Sync
Pull latest upstream changes into one or more vendor subtrees, cross-reference the diff against open upstream issue tracking entries, and re-link workspace packages.
Registry
Read the vendor subtree registry from .claude/vendor-registry.json. Each
entry has the shape:
{ "prefix": "vendor/pkg", "remote": "remote-name", "branch": "branch-name", "package": "@scope/pkg-name" }
- prefix — the local
vendor/directory used as the subtree prefix - remote — the git remote alias configured in this repo
- branch — the upstream branch to pull from
- package — the npm package name; maps to
UPSTREAM-<name>.mdfilename (slashes →--, drop leading@): e.g.@voxpelli/pkg→UPSTREAM-voxpelli--pkg.md
Optional fields:
- local-path — alternative on-disk path for the subtree if it does not
live at
prefix(rare; used for monorepo layouts or CI checkout paths). When absent, skills useprefixas the on-disk location.
If .claude/vendor-registry.json does not exist, offer to create it via
workflow 0 (Bootstrap registry). Do not attempt to read the subtree
table from any other source.
Local override file
.claude/vendor-registry.local.json is a gitignored companion that overrides
fields in the committed .claude/vendor-registry.json. It mirrors the
settings.local.json convention: machine-specific state stays out of version
control, while the committed registry documents the shared schema.
[
{ "package": "@scope/pkg-name", "local-path": "/abs/path/to/checkout" }
]
Resolution rules:
- Read
.claude/vendor-registry.json. - If
.claude/vendor-registry.local.jsonexists, read it and merge on top, matching entries by thepackagekey (the most stable identifier across machines). Fields present in.local.jsonwin; absent fields keep the base value. - Entries in
.local.jsonwhosepackagedoes not appear in the base registry are ignored — the base registry remains the authoritative source of which subtrees exist.
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.
- 9d ago First seen · 418 lines · 83 tokens per session scan C 9fb9694b78e5
vendor-sync is a skill published in the GitHub repository voxpelli/claude-beads (2 stars, last pushed 25d ago), licensed MIT. It adds 83 tokens to every session and 4,215 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
schema-evolve
This skill should be used when the user asks about 'schema drift', 'schema evolution', 'evolve schema', 'schema sync', 'sync schemas', 'update schema fields', 'schema field frequency', 'missing schema fields', 'unused schema fields', 'schema proposal', 'schema cardinality', 'check schema', 'schema audit', 'schema…
knowledge-garden
This skill should be used when the user asks to audit, health-check, or structurally validate one or more SPECIFIC named notes or a bounded topic cluster — 'audit these notes', 'check this note for orphans or broken links', 'fourth-wall check on [note]', 'validate the structure of [note]', 'spot-check [note]'. Runs a…
knowledge-maintain
This skill should be used when the user asks to fix, repair, or tidy one or more SPECIFIC named notes — 'fix these notes', 'fix the issues in [note]', 'add the missing relations to [note]', 'tidy up [note]', 'fix orphan [note]', 'apply the gardener findings for [note]'. Applies structural fixes (missing sections…
raindrop-triage
This skill should be used when the user asks to 'triage unsorted bookmarks', 'clean up raindrop inbox', 'sort unsorted', 'organize bookmarks', 'raindrop triage', 'process bookmark backlog', 'promote triaged bookmarks', 'classify triaged', 'raindrop cleanup', 'deduplicate bookmarks', 'find duplicate bookmarks', 'tag…
session-bookmarks
This skill should be used to save URLs or links found this session as Raindrop bookmarks — triggers: 'bookmark URLs from this session', 'save links we found', 'save notable URLs to Raindrop', 'save session URLs', 'raindrop bookmarks from session'. Scans the current conversation for high-signal URLs discovered during…
session-reflect
This skill should be used when the user asks to 'reflect on this session', 'save insights to memory', 'capture what we learned', 'commit this to memory', 'save decisions to Basic Memory', 'write up what we did', 'preserve what we found', 'save insights from this conversation', 'save what was discovered', 'capture…