oacp
foundationThe protocol primer — teaches a runtime how to use the CLI and message protocol. Foundation for every other skill.
$/oacp
Reusable agent skills · v0.5.2
A small library, deeply composed.
Each skill is a single, well-scoped capability — the workflow layer above the protocol. Drop-in for Claude Code and Codex CLI. Apache 2.0.
9
skills
5
categories
2
runtimes
1
spec
composition
Every session begins with
/oacp bootstrapping the runtime, then composes one or more skills as the work demands. /wrap-up closes the session — running debrief, self-improve, commit + push, and memory sync, in strict order.Foundation
/oacp
protocol awareness · loaded once per session
Composes
Coordination
check-inbox
processes any message
↕
review-loop
reviewer ⇌ author
Workspace
doctor
diagnostics + auto-fix
↕
self-improve
audits skills + memory
Memory
debrief
captures session
↕
sync
consolidates daily
Closes with
/wrap-up
debrief · self-improve · commit + push · memory sync
01 ·
Foundation
Core protocol awareness. Loaded once per session — teaches the runtime how to use the CLI and message protocol. Every other skill builds on it.02 ·
Coordination
Move work between agents safely — general-purpose inbox handling and the review-loop pair that closes the agent-to-agent code review cycle.check-inbox
General-purpose inbox processor. Scans for pending OACP messages of any type, processes each, then exits. Pair with a loop or oacp watch for continuous monitoring.
$/check-inbox
review-loop-reviewer
Reads a PR diff, produces structured findings, renders a verdict, and sends feedback to the author’s inbox. Supports multi-round reviews.
$/review-loop-reviewer 42 --author claude
review-loop-author
Picks up review findings, applies fixes, pushes updates, and sends a review_addressed message back. Closes the loop.
$/review-loop-author 42 --reviewer codex
03 ·
Workspace
Keep the workspace healthy — environment and inbox diagnostics, plus knowledge-layer audits across skills, memory files, and config.doctor
Wraps oacp doctor for self-diagnostics. Checks environment, workspace, inbox health, schemas, agent status. Auto-fixes safe issues.
$/doctor
self-improve
Audits the agent’s knowledge layer — skills, memory files, config — for staleness, contradictions, gaps, and bloat. Proposes surgical fixes.
$/self-improve
04 ·
Memory
Persist what was learned. Capture session summaries to the cortex inbox, and consolidate across projects into a single source of truth.debrief
Captures a structured session summary at end of session and sends it to the cortex inbox. Wrap-up calls this automatically; you can also run it standalone.
$/debrief
sync
Consolidates session debriefs across projects into a single source of truth (SSOT). Run once daily — typically each morning.
$/sync
05 ·
Lifecycle
Bookend a session well. Lifecycle skills orchestrate the end of every run — cleanup, debrief, self-improve, commit, push, sync — in strict order.wrap-up
lifecycleEnd-of-session orchestrator. Cleans up merged branches and stale worktrees, runs debrief and self-improve, commits, pushes, and syncs OACP memory — in strict order.
composes
↳debrief
↳self-improve
↳commit + push
↳memory sync
$/wrap-up
Install + wire
Three steps. Three minutes.
The CLI does the wiring. Skills land in the right place for each runtime — no manual symlinks, no per-agent config drift.
Read setup docs →install.sh
bash
01
# 1. install the cli
02
$ pip install oacp-cli
03
04
# 2. set up your runtime — wires the foundation skill automatically
05
$ oacp setup claude --project my-app
06
$ oacp setup codex --project my-app
07
08
# 3. invoke skills from inside the agent
09
claude → /oacp # foundation
10
claude → /check-inbox # coordination
11
claude → /wrap-up # lifecycle