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 agentmods add skills/fo0/clawstash/beaconnpx skills add fo0/clawstash --skill beacongit clone --depth 1 https://github.com/fo0/clawstashWhat 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 | $0.00000 | $0.01211 |
| Opus 5 | $0.00000 | $0.00606 |
| Sonnet 5 | $0.00000 | $0.00242 |
| Haiku 4.5 | $0.00000 | $0.00121 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 85 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_whoamiand 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; ordeclares_project: true— the shared master/onboarding token, bound to no project: then every call below MUST carryproject:"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.
2 · Start from tracked proposals (GitHub-connected projects)
- Call
compat_proposalswithproject:"fo0/clawstash": the open Dependabot PRs beacon tracks for this repo, each with a pre-computed verdict, reasons, and the PR link. Skip this step when the tool is missing or the response saysgithub.connectedis false. - Treat every open proposal as an update candidate for step 4 — prepared, not pre-approved:
beacon’s verdict stays a veto, and the
compat_planvalidation below still applies. - Never merge or close the Dependabot PR yourself. Apply an accepted bump through this
repo’s own branch/PR flow (steps 5–6) — Dependabot resolves its PR once the bump lands —
and record the outcome with
compat_decideeither way.
3 · Check the current stack
- Run
compat_checkwithproject:"fo0/clawstash"and the lock-exact stack (prefer the lockfile, e.g.package-lock.json; fall back to the manifest). - Read:
summary, flagged pairs inresults,derivedpeer/advisory findings, andrecommendations— beacon’s verified counter-proposals for flagged pairs.
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.
- 2d ago First seen · 85 lines · 0 tokens per session scan A 46f5e84ffb20
beacon is a skill published in the GitHub repository fo0/clawstash (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,211 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.
Other skills, from other repositories
user-usecases
Database of real user use cases for APIbase platform. Contains detailed examples of how specific APIs are onboarded, wrapped, and served to AI agents. Use this skill when you need to reference real integration examples, explain the APIbase onboarding process, or design new API wrappers based on proven patterns.
business-model-validator
Use when a prospect, new customer, or existing operator wants to know whether Zooza fits their business, or which Zooza features map to how they operate. No Zooza account required — works as a pure knowledge interview.
spotify-mcp-doctor
Diagnose and repair NovaLux12/spotify-mcp-server failures — auth, permissions, devices, rate limits, OpenClaw wiring. Use when Spotify tool calls fail or setup stalls.
delegacion-local
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
class-management
Use when the user wants to create a new class, group, or course in Zooza — e.g. "set up a Monday yoga class", "add a new group", "schedule a course". Guides through programme selection, venue, trainer, session pattern, and commits.
feedback-nudge
Use when the user wants to report a bug, request a feature, or send feedback to the Zooza engineering team. Also offer proactively after a successful commit operation (max once per week).