Every skill is a single SKILL.md file. Install
the full set or just the ones you want. No API keys, no package
manager, no build step.
Need the CLI first?
Install Claude Code
, open a terminal at your project root, then drop the skills
into .claude/skills/. Claude Code
auto-discovers them on the next session.
curl -L https://opchain.dev/opchain-skills.zip -o opchain-skills.zip
unzip opchain-skills.zip -d .claude/skills/
claude
> /oc-discover Verify it worked. In that session, type
/oc-discover. If oc-app-architect starts an
interview ("Who's the primary user? Sync or async? …"), you're
set. If not, re-check that the files landed in
.claude/skills/<name>/SKILL.md.
SKILL.md files from the Skill Library. .md file./oc-discover).
Commit the skills directory so every teammate uses the same prompt pipeline.
git add .claude/skills/
git commit -m "chore: add opchain skills"
git pushCodex — and any MCP-aware agent (Claude Desktop, Cursor, Windsurf) — reaches opchain over the Model Context Protocol. Point your client at the hosted endpoint and you get the catalog, intent routing, the orchestrator protocol, and checkpoints — the same pipeline Claude Code auto-discovers.
Hosted MCP server — nothing to install:
# ~/.codex/config.toml
[mcp_servers.opchain]
url = "https://opchain.dev/mcp" Or drop the skills in directly — Codex Agent Skills
use the same SKILL.md format:
curl -L https://opchain.dev/opchain-skills.zip -o opchain-skills.zip
unzip opchain-skills.zip -d .codex/skills/
codex Verify it worked. Run codex
and ask "build me an app" — opchain's route
tool (or an implicit skill match) hands you to oc-app-architect's
discovery interview. With the MCP server, the
/oc-* commands also appear as prompts in the
slash menu.
Already running opchain in a project? Replace the skills in place.
Your .checkpoints/ directory lives
outside .claude/skills/, so every
skill's session state — phase, step, next actions, decisions — is
preserved across the swap. The new skills pick up the existing
checkpoints on their next invocation.
Run from your project root. This wipes the old skills directory and replaces it with the latest bundle.
# .checkpoints/ is a sibling of .claude/ — never touched by this swap
rm -rf .claude/skills/
curl -L https://opchain.dev/opchain-skills.zip -o opchain-skills.zip
unzip opchain-skills.zip -d .claude/skills/
rm opchain-skills.zip Verify the new version is live. Check what the
site is currently shipping with
curl https://opchain.dev/api/health (the
version field is the build SHA), then
start a new Claude Code session and run
/oc-ops — the orchestrator should report your
existing checkpoints exactly where you left them.
SKILL.md files you use from the Skill Library.
If you committed .claude/skills/ with the
team flow, do the upgrade on a branch so the skill diff lands in
review:
git checkout -b chore/upgrade-opchain
rm -rf .claude/skills/
curl -L https://opchain.dev/opchain-skills.zip -o opchain-skills.zip
unzip opchain-skills.zip -d .claude/skills/
rm opchain-skills.zip
git add .claude/skills/
git commit -m "chore: upgrade opchain skills"
Reviewers see exactly which skills changed, and
.checkpoints/ is untouched because it's a
separate top-level directory.
curl -sS https://opchain.dev/api/health | jq .version
Returns the build SHA currently published at
opchain.dev. Re-run after upgrading and
confirm a fresh Claude session sees the new skills under
.claude/skills/<name>/SKILL.md.
.claude/skills/.checkpoints/orchestrator.md.codex/skills/~/.codex/config.toml[mcp_servers.opchain]..checkpoints/; pick up exactly where you left off, next chat or next weekWant a preview first? The demo walks you through six end-to-end opchain sessions, end to end.
No code yet · greenfield project
/oc-discover — oc-app-architect runs the spec interviewCode already on disk · no opchain history
/oc-rev-spec — oc-reverse-spec backfills a spec from the code/oc-ops for the orchestrator's read on what's openBug or feature already in progress