OPC — One Person Company. A full team in a single Claude Code skill. Adaptive agent orchestrator with 11 built-in roles, 4 modes, and adversarial quality control.
# Add to your Claude Code skills
git clone https://github.com/iamtouchskyer/opcLast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:57:14.628Z",
"npmAuditRan": true,
"pipAuditRan": true
}No comments yet. Be the first to share your thoughts!
30 days in the Featured rail
A full team in a single Claude Code skill. You're the CEO — OPC is everyone else.
16 specialist agents (PM, Designer, Security, Devil's Advocate, and more) that build, review, and evaluate your code through a digraph-based pipeline with code-enforced quality gates.
One principle: the agent that does the work never evaluates it.
Task → Flow Selection → Node Execution → Gate Verdict → Route Next
↑ ↓
└──────── ITERATE/FAIL ────────┘
Task inference — reads your request, picks a flow template (review, build-verify, full-stack, pre-release), and enters at the right node.
Typed nodes — each node has a type (discussion, build, review, execute, gate) with specific protocols. Build nodes produce commits. Review nodes dispatch parallel subagents. Gate nodes compute verdicts from code, not LLM judgment.
Mechanical gates — verdicts are computed by opc-harness synthesize: any red = FAIL, any yellow = ITERATE, all green = PASS. No LLM gets to decide if a finding is "important enough."
Cycle limits — max 3 loops per edge, 5 re-entries per node, 20-30 total steps depending on flow. Oscillation detection catches A↔B loops.

The system is built on a zero-trust axiom: every critical output must have an independent verification path. Four layers:
npm install -g @touchskyer/opc
Skill files are automatically copied to ~/.claude/skills/opc/.
git clone https://github.com/iamtouchskyer/opc.git
cp -r opc ~/.claude/skills/opc
# Review — dispatches 2-5 role agents in parallel
/opc review the auth changes
# Build — implements + independent review + gate
/opc implement user authentication with email/password
# Autonomous loop — decomposes, schedules cron, runs unattended
/opc loop build features F1-F4 from PLAN.md
# Interactive mode — asks clarifying questions first
/opc -i redesign the onboarding flow
# Explicit roles
/opc security devil-advocate
# Flow control
/opc skip # skip current node
/opc pass # force-pass gate
/opc stop # terminate, preserve state
/opc goto build # jump to node
/opc loop build the math tutoring app features F1-F4
What happens:
opc-harness runbook match "<task>" checks --dir flag → OPC_RUNBOOKS_DIR → ~/.opc/runbooks/ for a matching recipe. If one hits, its units / flow / tier become the plan; otherwise fall through to step 2. Disable per-invocation with OPC_DISABLE_RUNBOOKS=1. See docs/runbooks.md and examples/runbooks/add-feature.md.opc-harness enforces: git commit required, ≥2 independent reviewers, no plan tampering, no state forgery, artifact freshness, tick limitsFor well-scoped tasks, the system runs 10+ hours continuously without intervention.
| Guard | Enforcement | |-------|-------------| | Write nonce | Random SHA256 at init; state written by harness only | | Atomic writes | write → rename (POSIX atomic); no truncated JSON on crash | | Plan integrity | SHA256 hash at init; verified every tick | | Review independence | ≥2 eval files, identical content rejected, line overlap warned | | Git commit required | HEAD must change for implement/fix units | | Screenshot required | UI units must produce .png/.jpg artifact | | Tick limits | maxTotalTicks (units×3) + 24h wall-clock deadline | | Oscillation detection | A↔B pattern over 4-6 ticks = warning/hard stop | | Concurrent tick mutex | in_progress status blocks overlapping cron fires | | JSON crash recovery | try/catch on all JSON.parse; structured errors, not crashes | | External validators | Pre-commit hooks, test suites detected at init and leveraged |
| Template | Nodes | When | |----------|-------|------| | review | code-review → gate | PR review, audit, "find problems" | | build-verify | build → code-review → test-design → test-execute → gate | "implement X", "fix bug Y" | | full-stack | discuss → build → review → test → acceptance → audit → e2e → gates | Complex/vague requests | | pre-release | acceptance → audit → e2e → gates | "verify before release" |
OPC has a capability-routed extension surface. Extensions live in
~/.claude/skills/opc-extension/<name>/ — each with ext.json (capability
declarations) + hook.mjs exporting any of promptAppend / verdictAppend
/ executeRun / artifactEmit hooks. No fork, no rebuild. Hooks are
sandboxed via per-extension timeouts + circuit breakers, so a broken
third-party extension can't take down the harness.
The companion repo opc-extensions ships 4 extensions: design-intelligence (theme injection + design coverage + VLM visual eval), git-changeset-review, memex-recall, and session-logex.
Full authoring guide: docs/extension-authoring.md — zero-OPC-context
quickstart + reference, plus a starter template at examples/extensions/_starter/.
Product: pm, designer
User Lens: new-user, active-user, churned-user
Engineering: frontend, backend, devops, architect, engineer
Quality: security, tester, compliance, a11y
Specialist: planner, user-simulator, devil-advocate
Devil's Advocate (the 10th person) is auto-included when consensus is near-unanimous or decisions are irreversible. Comes with an automated verification script that checks its own findings.
Add a .md file to roles/:
---
tags: [review, build]
---
# Role Name
## Identity
One sentence: who you are and what you care about.
## Expertise
- **Area** — what you know about it
## When to Include
- Condition that triggers this role
Available immediately, no configuration needed.
bash test/run-all.sh
100+ test files covering init-loop, complete-tick, next-tick, review independence, JSON crash recovery, compound defense, scope registry, criteria lint, pipeline E2E lint, D2 calibration, release packaging, and orchestrator-level E2E flow tests.
jq for opc install-hooks context-compaction hooksOPC works standalone — pair it with memex for cross-session memory. Memex remembers which roles were useful, which findings were false positives, and your project-specific context.
npm install -g @touchskyer/memex
See CHANGELOG.md for version history.
Using OPC? Share your setup in Discussions → Show and tell. Questions go in Q&A. Feature ideas in Ideas.
MIT