nexus
Skill158 starsChanged 6 days agoMITView on GitHub
Read, search, and edit the user's Obsidian vault (notes, folders, canvas, bases, tasks, memory/workspaces, saved prompts) from the shell via the `nexus` CLI — no MCP connection needed. Use whenever the user refers to their vault, notes, daily notes, second brain, or Obsidian, or asks you to find/read/change something stored there and the `nexus` command is on PATH. Do not use it to edit files in the current code repository; use normal file tools for those.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- AntreasAntoniou/nexustheir own version, first seen Nov 8, 2026
- simota/agent-skillstheir own version, first seen Oct 23, 2026
- Eskyee/agentbot-opensourcetheir own version, first seen Oct 13, 2026
- BankrBot/openclaw-skillstheir own version, first seen Oct 8, 2026
- aayushostwal/nexustheir own version, first seen Aug 10, 2026
- GPire/claude-skills-swarmtheir own version, first seen Jun 30, 2026
Used with
Projects with it also use aeon-autoresearch, aeon-deal-flow and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
BankrBotSkillaeon-autoresearch
Evolve any installed skill by generating four variations along separate theses (better inputs / sharper output / more robust / rethink), scoring them on a weighted rubric, and applying the winner. Never downgrades a working skill — aborts cleanly if no variation improves the original. Use when an installed skill is producing low-signal output, hitting deprecated APIs, or feels stale. Triggers: "improve this skill", "evolve $skill", "auto-research my X", "regenerate variations".
Also in 3 projects that use this
BankrBotSkillaeon-deal-flow
Weekly funding round tracker across configurable verticals (AI, crypto, prediction markets, agentic infrastructure, etc.). Primary-source-required (Form D, press release, or verified founder/firm post) — filters re-announcements and rumored rounds. Per round: lead, size, valuation if disclosed, what they do, why now, and the sharpest risk. Triggers: "this week in funding", "deal flow", "who raised this week", "crypto funding rounds", "AI funding tracker".
Also in 3 projects that use this
- +10 more from BankrBot
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- BankrBot/openclaw-skills★ 1.2ksame name
- BankrBot/skills★ 1.2ksame name
- simota/agent-skills★ 96same name
- aayushostwal/nexus★ 19same name
- Eskyee/agentbot-opensource★ 17same name
- GPire/claude-skills-swarm★ 8same name
- Aether-liusiqi/nexus★ 2same name
- AntreasAntoniou/nexus★ 0same name
- InfiniteRoomLabs/agent-ops★ 0same name
- terrene-foundation/pact★ 0same 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- nexus-agentsSkill
- nexus-eval-harnessSkill
- nexus-llm-adaptersSkill
- nexus-mobile-compatSkill
- nexus-model-evalSkill
- nexus-model-updatesSkill
- nexus-releaseSkill
- nexus-storageSkill
- nexus-testingSkill
- nexus-tool-schemasSkill
- nexus-ui-mockupsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Explore → inspect → exploit: Search/list find *locations*.
- Very specific: line 62
Add --session <name> --workspace <name> to the first use of a task only.
- Very specific: line 74
Pass a tool's required value positionally: Write memory load-workspace "Silicon Zone", not memory load-workspace --workspace "Silicon Zone".
“Common” is measured: kept by at least 6 in 10 of the 8 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
Nexus vault CLI
nexus drives a running Nexus (Obsidian) vault from the shell over a local
socket — no MCP config. It has two verbs: discover what you can do, then
execute.
Start here
Run nexus --help first. It is the authoritative, always-current manual —
commands, the context contract, CLI syntax, gotchas, and the tool catalog. It's
offline and instant (no socket), so read it before your first real command
instead of guessing.
For a common task, nexus playbook <name> gives you a ready-to-run recipe
plus your workspaces and the exact tools it needs, in one call. Run
nexus playbook to see what's available (typically: vault-work, organize,
tasks, prompt).
The mindset (this is what --help can't teach you)
- Explore → inspect → exploit. Search/list find locations;
content readgets contents; then you write. A search hit is a{path, score}, not the note — never quote, summarize, or edit from a hit without reading it first. nexus toolsreturns schemas, not data. It's discovery. Don't loop it hoping for vault content — that comes fromnexus use --memory … --goal … -- content read ….--memoryand--goalare real and enforced. You're operating a person's live vault; pass a genuine running summary and objective, not placeholders.--workspaceand--sessionare pass-once. The vault remembers them: name a session and choose its workspace on the first call of a task (or runmemory load-workspace <name>), then omit both — every later call continues that session and inherits its workspace. Nothing defaults silently: a session that never chose a workspace fails with "This session has no workspace yet" (onlymemory list-workspaces/load-workspace/create-workspacerun before the choice). Pass a different value once to switch.nexus contextshows what the vault currently remembers.- You can't escape the vault. Paths are vault-relative;
..,~, and absolute paths are rejected. That's a guardrail, not a bug. - Nothing is destroyed. The AI gets archive (reversible), not delete.
- Windows:
nexus vaultsdiscovers local named pipes. If policy blocks enumeration, pass--vault <name>or setNEXUS_VAULT.
The shape
nexus tools [selector] # discover — tool schemas (never vault data)
nexus use --memory "<what you're doing>" --goal "<objective>" -- \
<agent command --flags> # execute — runs one tool, prints the result
nexus context # what this vault remembers: session + workspaceAdd --session <name> --workspace <name> to the first use of a task
only; the vault remembers both for every call after it.
The -- delimiter is canonical: context belongs before it; the tool command
belongs after it. This avoids nested command-string quoting, especially in
Windows PowerShell. The legacy one-string form remains supported.
Three rules that cover almost every way this goes wrong:
--splits the two halves, and only that. Context flags (--memory,--goal,--session,--constraints,--vault) go before it; the agent name, tool name, and every tool flag go after it.- Pass a tool's required value positionally. Write
memory load-workspace "Silicon Zone", notmemory load-workspace --workspace "Silicon Zone".--workspaceis also a context flag, so the positional form is the one that can't be misread. - Keep the agent name with the tool name. The command after
--is always<agent> <tool> [flags]—storage list, notlist. - Context flags may sit before or after the verb.
nexus --vault V use …andnexus use --vault V …are equivalent.
Malformed commands fail loudly with the corrected command in the error text — read it and retry rather than switching syntax forms. Nothing is silently dropped, so an error never means a partial write happened.
For multiline Markdown or content containing embedded quotes, keep the body
out of shell argv. Any value-taking tool flag has a transport form: pipe with
--<flag>-stdin or pass a local path with --<flag>-file (e.g.
--content-stdin, --conversation-context-file ctx.md). Put the transport
after the -- delimiter and do not also pass the flag directly. Never flatten
multiline content to one line to dodge quoting:
Get-Content -Raw .\note.md |
nexus use --memory "importing note" --goal "write note" -- content write --path Notes/Imported.md --content-stdinEverything else — the flag table, per-tool schemas, syntax rules, the live
per-vault catalog (including any enabled app agents) — comes from nexus --help,
nexus tools <tool>, and nexus playbook <name>. Prefer those over guessing;
they're always current.
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.

