A dependency health and update workflow for a software project. Dependencies are external packages the project relies on; this workflow checks them and evaluates proposed updates through the Beacon compatibility service.

Use it to review tracked Dependabot proposals, inspect the project’s current package stack, and propose or apply dependency updates. Automatic runs apply only the updates judged safe.

It helps separate updates that are likely safe from updates that may break the project. It also verifies that the service is connected to the correct repository before checking or changing anything.

How fo0/clawstash configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fo0/clawstash. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/fo0/clawstash/main/.claude/skills/beacon/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/fo0/clawstash

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fo0/clawstash/beacon/github.svg)](https://agentmods.dev/skills/fo0/clawstash/beacon)

Your own site

<a href="https://agentmods.dev/skills/fo0/clawstash/beacon"><img src="https://agentmods.dev/badge/skills/fo0/clawstash/beacon/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fo0/clawstash/beacon"><img src="https://agentmods.dev/badge/skills/fo0/clawstash/beacon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,556 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.01556
Opus 5.5	$0.00000	$0.00622
Sonnet 5.5	$0.00000	$0.00311
Haiku 4.5	$0.00000	$0.00156

Measured 7d ago against content hash 417b28fdb7b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

beacon 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 7d 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.

.claude/skills/beacon/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

beacon — check the stack, propose updates, apply only what is safe

Goal: use the beacon MCP tools (compat_*) to (1) pick up the Dependabot proposals beacon already tracks, (2) check THIS project’s current stack, (3) propose dependency updates with beacon’s verdicts attached, and (4) apply them — all of them only when the user picked them; ONLY the safe subset when running autonomously.

1 · Verify identity (every run)

Call compat_whoami with skill_version = the version on this file’s beacon-skill-version line (just below the frontmatter), and confirm it agrees with this repo ("fo0/clawstash", i.e. git remote get-url origin). Exactly two results are OK:
- project: "fo0/clawstash" — a token bound to THIS project; or
- declares_project: true — the shared master/onboarding token, bound to no project: then every call below MUST carry project:"fo0/clawstash" (repo: on report/observe), which is what attributes the run. This skill already passes it everywhere.
Any other project → STOP and tell the user to re-onboard via beacon’s /onboard page; never write under another project’s token.
Then read skill.status in the same answer — whether THIS file is still current:
- outdated → call compat_skill with project:"fo0/clawstash", then:
  - replace everything above a ## 8 · This repo section with its content verbatim and keep that section verbatim after it (if this file has one);
  - commit that refresh on its own — only this file, its own commit. Unattended: on the run’s own branch, inside its PR; a run that would open no PR opens one for this file alone (never straight to main). Interactive: propose that one-file commit to the user and keep it out of other work;
  - tell the user (unattended: note it in the run’s summary or PR), then continue with the NEW file’s instructions, not these.
- current → continue. unknown → skill_version did not arrive; call again with it.
- No skill block at all (an older beacon) → continue as before.

Read the full file on GitHub · 102 lines

Changes

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.

7d ago Changed · +14 lines 417b28fdb7b6
21d ago Changed · +3 lines 628e91570f8f
2mo ago First seen · 85 lines · 0 tokens per session scan A 46f5e84ffb20

Subscribe to this mod's changes

beacon is a skill published in the GitHub repository fo0/clawstash (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,556 tokens. 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.

DevOps and cloud ai-tools api developer-tools mcp mcp-server model-context-protocol

@elad12390/web-research-assistant

Comprehensive MCP server for web research with 16 tools: SearXNG + Exa AI search, batch search and batch crawling, URL crawling, stealth scraping (Cloudflare bypass), package registry lookup (npm/PyPI/crates), GitHub stats, changelog fetching, tech comparison, error translation, API docs discovery, stock image search…

elad12390/web-research-assistant · 150 tokens

football-data

Look up or code against football (soccer) statistics from Football Charts, covering results with half-time scores, league tables, fixtures, goal timing and season projections for 98 leagues, including lower divisions. Use when the user asks about football results, tables or fixtures, or writes code that needs football…

ddevetak/footballcharts-mcp · 65 tokens

clawstash: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

beacon — check the stack, propose updates, apply only what is safe

1 · Verify identity (every run)

What this file has done since we first saw it

Other skills, from other repositories

@elad12390/web-research-assistant

football-data

publish-release

spotify-mcp-doctor

internet-archive-guide

class-management