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 ashfulcra/fulcra-tools --skill fulcra-agent-durable-stategit clone --depth 1 https://github.com/ashfulcra/fulcra-toolsWrote 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-durable-state)<a href="https://agentmods.dev/skills/ashfulcra/fulcra-tools/fulcra-agent-durable-state"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-durable-state/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-durable-state"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-durable-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.01692 |
| Opus 5 | $0.00028 | $0.00846 |
| Sonnet 5 | $0.00011 | $0.00338 |
| Haiku 4.5 | $0.00006 | $0.00169 |
Grade A, and why
fulcra-agent-durable-state 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 11d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fulcra Agent Durable State
Ephemeral compute + durable Fulcra state = agents that survive their machines.
Cloud agent containers get reclaimed and rolled back. Desktop hosts sleep, reboot, and disappear. Any agent whose tooling lives only on local disk is one filesystem event away from amnesia — and worse than losing a script is silently regaining an old one: a rollback can revert a patched loop to the unpatched version, or restore a rotated credential's stale predecessor, and nothing errors until it misbehaves.
The Fulcra File Store is the piece of the platform that doesn't share the machine's
fate. It's the same substrate the coordination bus runs on (versioned,
last-writer-wins, survives every container the fleet has lost so far), and
fulcra-api auth persists independently of scratch disk. So the pattern is:
Local disk is a cache. The store is the truth.
Where to start — the re-entrancy probes
Before touching the stash, probe how far this session already got. Enter at the first probe
that fails (per the repo's skill-quality pattern, docs/skill-quality-pattern.md); every step
is safely re-runnable (uploads/downloads are whole-file overwrites, last-writer-wins). Auth
probes on fulcra-api (the engine inherits its credentials); the stash probes run on the
engine's stash verb:
| Probe (run in order) | Command | Passes when | If it fails, enter at |
|---|---|---|---|
| Auth usable? | fulcra-api auth print-access-token >/dev/null && echo AUTH-OK |
prints AUTH-OK (exit 0) |
fulcra-api auth login — browser sign-in; a headless agent that can't complete it should surface to its operator, not improvise |
| Stash exists? | coord-engine stash list <team> --agent <agent> |
lists at least one file (not empty) |
First adoption — nothing durable yet: push your bundle now (see On change below) |
| Local cache complete? | test -x <local-path> for each tool the stash lists |
every tool you depend on exists locally and is executable | Restore — coord-engine stash pull <team> --agent <agent> --dest <dir> (see On wake below) |
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.
- 11d ago First seen · 124 lines · 55 tokens per session scan A bb4017e002ee
fulcra-agent-durable-state is a skill published in the GitHub repository ashfulcra/fulcra-tools (10 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,692 once invoked, about $0.0003 per session on Opus 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
magic-compact
Compact this Claude Code session.
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…