Agent skills

Install GNO as a progressive agent skill for Claude Code, Codex, OpenCode, OpenClaw, Hermes Agent, and compatible clients.

GNO skills teach agents how to use the gno CLI without permanently loading a large tool schema into their context. Use them for explicit /gno lookups from Claude Code, Codex, OpenCode, OpenClaw, Hermes Agent, and other skill-capable clients.

What this is

Progressive instructions — the agent discovers the GNO workflow only when you invoke the skill or ask for local knowledge retrieval.
CLI-backed — skill commands call the installed gno binary, so results match the terminal.
Ask the agent to run /gno over notes, project docs, PDFs, or meeting notes before it answers.
Second-brain recipes — installed playbooks route agents through lookup, capture, meetings, email context, source summaries, ideas, and citation/provenance workflows.

Install

gno skill install --scope user # Claude Code default
gno skill install --target codex --scope user
gno skill install --target opencode --scope user
gno skill install --target openclaw --scope user
gno skill install --target hermes --scope user
gno skill install --target all --scope user --force

--target — claude, codex, opencode, openclaw, hermes, or all.
--scope — user for every project or project for the current repo.
--force — overwrite an existing installed copy after upgrading GNO.

Teach your harness how to retrieve

For a second brain or LLM wiki, install the connector and the retrieval protocol together. The skill or MCP connector gives the harness access to GNO. The instruction block teaches when to retrieve, how to choose an efficient search path, and how to cite and maintain knowledge.

gno agents install
gno agents verify

This covers detected supported harnesses. Use --target codex, for example, to select one. Text outside the managed block stays unchanged. See agent instructions for supported targets and clients that need manual guidance. Start a fresh session and ask a question answered by your indexed files; verify retrieval and a source citation. The verify command checks the block, not model behavior.

Skill management commands

gno skill install — copy the bundled skill into the selected target.
gno skill uninstall — remove it.
gno skill show — preview the generated skill files.
gno skill show --file recipes/brain-first-lookup.md — preview a nested recipe playbook.
gno skill paths — show target install locations.

Distribution and updates

The local installer copies the skill bundled with your installed GNO release. After upgrading GNO, refresh your chosen target and its instruction block. The force flag replaces local skill edits; preserve customizations first.

gno skill install --target hermes --scope user --force
gno agents update --target hermes
gno agents verify --target hermes

Prefer registry-managed skills? OpenClaw users can install the GNO ClawHub bundlefrom their workspace. Hermes supports the same registry, but its scanner may require review of the MCP configuration examples. Prefergno skill install --target hermes --scope user for a complete local installation. Install the GNO executable separately and add the retrieval protocol with gno agents install.

# Run from the OpenClaw workspace
bunx clawhub@0.23.3 install @gmickel/gno
bunx clawhub@0.23.3 update @gmickel/gno

# Hermes hub
hermes skills install clawhub/gno
hermes skills check
hermes skills update gno

Choose one installer per skill directory. A bare SKILL.md URL can omit supporting recipes; the bundled installer copies the whole skill. Release publication does not update existing installations. For unattended updates, schedule the native update command for the chosen skill under the same user and workspace, retain logs, and leave updates needing approval pending. Upgrade GNO before refreshing its skill, then run gno agents update. Start a fresh session afterward.

Skills and instruction blocks guide retrieval. The optional Hermes memory provider and OpenClaw memory pluginintegrate with the harness memory lifecycle and need separate setup.

Using the skill

/gno search "deployment checklist"
/gno query "what did I save about spaced repetition?"
/gno ask "summarize my notes on local-first software"
/gno graph --neighbors gno://notes/llm-memory.md

Natural language works too: “search my notes for the latest pricing decision,” “find related docs before you edit this file,” or “use GNO to retrieve my notes about this client.”

Second-brain recipes

Recipes are agent-facing guidance files, not native connectors. Email, calendar, chat, and web material must be user-supplied or exported unless a separate tool provides it.

gno skill show --file recipes/brain-first-lookup.md
gno skill show --file recipes/capture-and-file.md
gno skill show --file recipes/meeting-ingestion.md
gno skill show --file recipes/email-context.md
gno skill show --file recipes/source-summary.md
gno skill show --file recipes/idea-capture.md
gno skill show --file recipes/citation-and-provenance.md

Write-flavored recipes include provenance, privacy, prompt-injection handling, and post-write verification with gno index, gno embed, gno search, gno query, or gno get.

Instruction block: teach every agent the retrieval ladder

A skill only helps once the agent decides to call it. gno agents install writes one compact, versioned GNO protocol block into the global instruction file of every harness detected on the machine (Claude Code's ~/.claude/CLAUDE.md, Codex's ~/.codex/AGENTS.md, Cursor's ~/AGENTS.md, OpenCode, Hermes, OpenClaw; Grok Build is covered through its Claude import). The block teaches the retrieval ladder, the writing contract, gno:// citations, and points at the /gno skill. Everything outside its markers is yours and stays byte-identical.

gno agents install # every detected harness
gno agents install --dry-run # unified diff, writes nothing
gno agents install --extra-dir ~/.claude-instances/work-cli
gno agents verify # exactly one block, version + hash current
gno agents update # after a gno upgrade
gno agents uninstall

Backup-first (<file>.gno-agents.bak.<timestamp>), atomic, idempotent, symlink-aware, and never guesses: nonstandard layouts use the repeatable --extra-dir flag. If a file cannot be updated (malformed markers, not UTF-8, unwritable), the command prints the complete block so you can paste it yourself.

Use skills for explicit slash-command lookups and low context overhead.
Use MCP when you want the AI client to automatically call tools during conversation.
Installing both is normal: skills for direct control, MCP for deeper agent integration.

Typed metadata filters

Use fixed filters for tags, dates, categories, authors, and collections; use filter for explicit custom gno.metadata fields. Types are strict. ne/nin require a present field, while not(eq)/not(in) can match missing fields. Preserve filters and inspect coverage warnings before broadening a query.

Read the metadata guide: examples, operators, missing fields, limits, and recovery.

Past agent sessions

Installing the skill or an MCP connection does not import the agent's own conversations. If you want past Codex, Claude Code, OpenClaw, or Hermes sessions searchable, import them manually into a dedicated archive with its own config and index, kept apart from your curated vault, or opt in to a Claude Code SessionEnd hook or daemon schedule for that archive. Search it by passing that --config and --index; mixing it into the curated index is an explicit opt-in. Read the session archive guide.