Built for Codex CLI workflows
Sprint Tickets,
In Codex CLI.
OpenAI's Codex CLI runs agentic coding tasks straight from your terminal. Wire SprintFlint in and Codex pulls the next ticket, ships it, and posts the comment back.
5-min setup
REST API + MCP server
No card to start
Why OpenAI Codex CLI + SprintFlint
Built around how your AI actually works.
Other tools
- Codex CLI has no native ticket awareness
- OAuth dances kill the speed of a CLI loop
- No agent-readable spec
- Per-seat pricing punishes the agent seat
SprintFlint
- Public MCP server at mcp.sprintflint.com; native protocol
- Bearer-token auth, one header, no OAuth dance
- REST endpoints designed for agent-first workflows
- £5/user/mo, free tier covers your first 300 tickets
Step 1: Token
Token in env.
export SPRINTFLINT_TOKEN=sf_pk_your_token_here
# smoke test
curl -H "Authorization: Bearer $SPRINTFLINT_TOKEN" \
https://sprintflint.com/api/v1/dashboard
Step 2: codex.toml
Tell Codex CLI the workflow.
Add a SprintFlint hook in your Codex config so it pulls ticket context before each task.
# ~/.codex/config.toml
[tools.sprintflint]
url = "https://sprintflint.com/api/v1"
auth = "Bearer $SPRINTFLINT_TOKEN"
usage = "Fetch ticket context before coding. Post a comment after committing."
Step 3: Loop
Run, ship, comment.
codex "implement next SprintFlint ticket"; Codex fetches your sprint, picks the next undone ticket, codes, tests, and comments.
- Agent reads sprint backlog
- Auto-updates status when work begins
- Posts progress comments as it goes
- Pairs with Autoplay for full one-click PRs
Other AI editors we support
Same setup, different tools.
Codex CLI Already Codes.
Now it tracks the work too.
300 free tickets. Set up before lunch.