Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ashfulcra/fulcra-toolsnpx agentmods add skills/ashfulcra/fulcra-tools/fulcra-agent-cloud-coordinatorWrote 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/ashfulcra/fulcra-tools/fulcra-agent-cloud-coordinator)<a href="https://agentmods.dev/skills/ashfulcra/fulcra-tools/fulcra-agent-cloud-coordinator"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-cloud-coordinator/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/ashfulcra/fulcra-tools/fulcra-agent-cloud-coordinator"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-cloud-coordinator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 139 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00046 | $0.03338 |
| Opus 5.5 | $0.00018 | $0.01335 |
| Sonnet 5.5 | $0.00009 | $0.00668 |
| Haiku 4.5 | $0.00005 | $0.00334 |
Grade A, and why
fulcra-agent-cloud-coordinator 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 1mo 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fulcra Cloud Coordinator
Turn one Claude Code cloud session (claude.ai/code) into a persistent coordinator: an agent with a durable identity that wakes on schedules, reads the bus, dispatches and reviews work, and survives its own container being destroyed — because the session persists across containers and every scrap of state lives in the Fulcra store, not on the machine.
This is the OpenClaw/Hermes experience (persistent identity, heartbeat, durable context) rebuilt on managed cloud infrastructure you don't operate. The recovery principle is:
The machine is disposable, the agent is permanent, and the context lives in the store.
Where to start — re-entrancy probes
Run in order; enter at the first probe that fails.
| Probe | Command / check | Passes when | If it fails, enter at |
|---|---|---|---|
| Cloud session exists? | You are reading this INSIDE a claude.ai/code cloud session | yes | §1 (create environment + session) |
| Store reachable? | fulcra-api user-info |
prints your account | §2 (auth; remote-sandbox walls) |
| Engine present? | coord-engine --help |
verb list prints | §2 (install) |
| Identity established? | fulcra-api file download team/<team>/_coord/agents/<you>/census.md - |
your census prints | §3 |
| On the bus? | coord-engine queue <team> --agent <you> |
rc 0 plus a handled/committed delivery (if schema v2), no VERSION WARNING/INCOMPATIBLE result | §3 |
| Recovery self-heals? | ls scripts/<you>/bootstrap.sh in the repo checkout |
exists | §4 |
| Wakes armed? | your standing schedules exist (see §5's inventory check) | every duty has a wake | §5 |
| Duties silent-when-healthy? | last several duty runs produced no operator noise | quiet | §6 |
All pass → you are the pattern; keep the doctrine (§7) and maintain your
harness doc (docs/coord/agents/<you>.md).
1. The environment (one-time, human)
In claude.ai/code, create an environment for the repo (session menu → environments):
- Network: Full, or Custom allowing at minimum
fulcra.us.auth0.comandapi.fulcradynamics.com(the bus), plus anything your duties call. - Secrets via environment config, never via chat or files: add env vars
(e.g.
LINEAR_API_KEY) in the environment's configuration. Duty scripts materialize their own 0600 env files from injected vars on each container (see §4) — a fresh container needs zero secret handling. - Setup script (optional but recommended): restore duty tooling from the store stash before the agent wakes (the same commands as §4's self-heal).
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.
- 1mo ago Changed · -3 lines 45ef5df90638
- 1mo ago Changed 2cd51aa09746
- 1mo ago First seen · 262 lines · 46 tokens per session scan A 584eb68daf70
fulcra-agent-cloud-coordinator is a skill published in the GitHub repository ashfulcra/fulcra-tools (10 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 3,338 once invoked, about $0.0002 per session on Opus 5.5. 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
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
activate-site
Activates and provisions a Power Pages website in a Power Platform environment via the Power Platform REST API. Use when the user wants to activate, provision, turn on, or enable a Power Pages website or portal.
deploy-to-connect
Deploy or publish Python and R content to a Posit Connect server using rsconnect-python or the R rsconnect package. Handles interactive apps and dashboards, web APIs, rendered documents, and prepared bundles/manifests. Use whenever the user asks to deploy, publish, or redeploy content to Posit Connect, or mentions…
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…