Three commands in.
Memory on every prompt.

01 / Set up once

One command. Everything local.

1. 1Run the installer inside your repository

   Inside a git repo it installs the onecue CLI and runs onecue install — which writes the skill, the recall hooks, and the local store for each agent it detects. Nothing else to wire up.

   $curl -fsSL https://onecue.sh/install.sh | sh

   Store: ~/.onecue/projects/<project-fingerprint>/ · Hooks: .claude/settings.local.json + .devin/config.local.json · Skill: .claude/skills/onecue + .devin/skills/onecue

   Prefer npm? npm i -g onecue-cli, then onecue install. Skill only, no hooks? npx skills add onecueai/onecue-skill.

   Devin also reads .claude/ hooks by default — set read_config_from.claude: false in ~/.config/devin/config.json if you want a single source.

02 / Use it

Capture once. Recall when it matters.

1. 2Save something worth keeping

   From the terminal — or just tell Claude Code “remember that we chose Postgres for the job queue” and the skill captures it.

   $onecue remember "Keep the job queue in Postgres — order and job commit atomically." --kind decision
   • decisiona choice with a reason — architecture, libraries, trade-offs
   • insightsomething learned about the codebase that isn't written down
   • open_loopunfinished work or a thread to pick back up
   • discoverya debugging finding — cause, fix, or dead end
   • referencea pointer worth keeping — doc, config, or convention

2. 3Let recall happen

   With hooks installed, each new prompt gets at most one relevant cue — silence when nothing applies. Check what would surface, or browse the store, any time:

   $onecue recall "add retries for failed jobs"

   onecue list · onecue show <id> · onecue forget <id>

03 / Verify

Check the setup before blaming the memory.

onecue status shows which agents were detected and which have hooks; the doctor verifies the whole chain.

1. 4Run the doctor

   Runtime, store, per-agent hooks and skill, and memory integrity. Exits non-zero on warnings, so it fits CI.

   $onecue doctor

   No CLI? The companion skill ships the same checks as a script: onecue-doctor

Reference

Every command.

onecue init

Create the project store (~/.onecue/projects/<fingerprint>)

onecue install

Add recall hooks to .claude/settings.local.json

onecue uninstall

Remove only OneCue's hooks — memory is kept

onecue status

Initialization, hooks, and memory counts

onecue doctor

Diagnose the setup — seven checks, --json supported

onecue remember <text>

Save a memory [--kind …] [--reason …] [--files a,b]

onecue recall <context>

Print the one cue a context would surface

onecue list

List memories [--kind <k>] [--json]

onecue show <id>

Show one memory by id or prefix

onecue forget <id>

Delete one memory by id or prefix

Two stores, one purpose: the skill writes Markdown to .onecue/memories/ in the repo; the CLI keeps records in ~/.onecue/projects/. The doctor checks both.