slaunt
DOCUMENTATION

Agent instructions

Hooks report the lifecycle, but only the model can decide to search Slaunt Context before working or log a decision afterwards. The agent instructions tell it when to. slaunt-install appends them to the files Claude Code and Codex read at startup.

npx slaunt-install

It only appends, between start and end markers, so rerunning it is safe and your existing text is untouched. It refuses symlinks, non-UTF-8 and oversized files rather than risk corrupting them.

Where it writes

AgentDefault (user scope)Override
Codex~/.codex/AGENTS.override.md if it exists, else ~/.codex/AGENTS.mdCODEX_HOME
Claude Code~/.claude/CLAUDE.mdCLAUDE_CONFIG_DIR

With --scope project it writes to the Git root instead, which is useful if you want the instructions committed for your team. Codex uses AGENTS.override.md or AGENTS.md. Claude Code uses CLAUDE.md, then .claude/CLAUDE.md, else creates CLAUDE.md.

Flag
--scope user|projectDefault user
--only codex|claude|bothDefault both
--instructions <path>Use your own Markdown instead
--codex-path, --claude-pathWrite to a specific file
--project-dir <path>Repo root when not running inside it
--dry-run, --pathsPreview without writing

For Cursor and other clients, paste the raw text from /api/agent-instructions into the client's rules, e.g. .cursor/rules/slaunt.mdc.