inventory
Skill3 starsChanged 49 days agoMITView on GitHub
Discover, verify, and maintain Solana validator host and instance facts, including roles, paths, signer roles, and failover relationships. Use when adding servers or refreshing host layout; chain profiles, RPC configuration, and SFDP identity-pair setup belong to onboarding.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- z0rd0n88/claude-code-inventorytheir own version, first seen Nov 8, 2026
- Littlpinguin/marketing-cockpit-templatetheir own version, first seen Nov 3, 2026
- easyaitech/etsy-skillstheir own version, first seen Oct 16, 2026
- pantalytics/odoo-mcp-protheir own version, first seen Oct 12, 2026
- neurawork-git/n8n-autopilottheir own version, first seen Oct 1, 2026
- ulises-jeremias/agent-toolkittheir own version, first seen Aug 31, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- pantalytics/odoo-mcp-pro★ 91same name
- ulises-jeremias/agent-toolkit★ 19same name
- neurawork-git/n8n-autopilot★ 18same name
- Littlpinguin/marketing-cockpit-template★ 9same name
- easyaitech/etsy-skills★ 5same name
- z0rd0n88/claude-code-inventory★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- doublezero-statusSkill
- jito-bam-boostSkill
- jitosol-stewardSkill
- marinade-bond-sweepSkill
- onboardingSkill
- sfdp-checkSkill
- upgrade-agave-primarySkill
- upgrade-agaveSkill
- upgrade-mainnetSkill
- upgrade-testnetSkill
- validator-performanceSkill
- validator-revenueSkill
- votex-roi-simSkill
- votex-statusSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Read installed bundle and configuration before running commands.
- Distinctive: line 21
Read the shared inventory only when the task depends on host layout.
- Distinctive: line 22
Verify relevant facts through user confirmation or read-only SSH/RPC checks before changing them.
- Distinctive: line 23
Ask only for facts that cannot be discovered safely.
- Distinctive: line 24
Update current facts and the check timestamp.
- Distinctive: line 25
Treat unknown or stale facts as blockers for destructive operations.
- Very specific: line 40
When updating Markdown, preserve created and set last_updated in frontmatter.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Validator Inventory
Read installed bundle and configuration before running commands. Resolve paths from this loaded SKILL.md, not the session working directory.
Own host and signer facts for both new and existing instances. Read host and signer inventory for discovery and verification. Use the operator-selected VALIDATOR_OPS_HOST_INVENTORY or ~/.config/validator-ops/hosts.md. Never default to a private fleet bundled in an existing checkout. Reuse an explicitly selected inventory after checking relevance and freshness.
For missing or outdated chain profiles, RPC references, or SFDP identity-pair configuration, use onboarding. Host observations, chain profiles and local signer roles are separate evidence; none establishes the others or grants execution authorization.
Workflow
- Read the shared inventory only when the task depends on host layout.
- Verify relevant facts through user confirmation or read-only SSH/RPC checks before changing them.
- Ask only for facts that cannot be discovered safely.
- Update current facts and the check timestamp; remove superseded detail instead of accumulating history.
- Treat unknown or stale facts as blockers for destructive operations.
Keep
- Active aliases and roles.
- Cluster, client/version, identity, vote account, RPC, config, ledger, accounts, key paths, and service/screen.
- Failover relationships and safety constraints.
- A short note for unreachable or retired aliases when it prevents misuse.
Omit
- Private keys, seeds, passwords, API keys, SSH keys, and tokens.
- Full command logs, migration narratives, old hardware snapshots, and per-refresh changelogs.
- Superseded values already recoverable from Git history.
When updating Markdown, preserve created and set last_updated in frontmatter. Report UTC and local check time.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.