changelog

Changelog.

What shipped, what's next, and what to do about it. Each skill's version field is the source of truth — this page rolls them up by release. Vote on what's coming to signal priority.

What shipped

Newest is open; click any release for full notes.

Four new skills

oc-claude-api · /oc-claude-api

Model routing (Opus/Sonnet/Haiku/Fable), prompt caching by default, streaming vs. batch, tool use, and migration playbooks for model-version bumps.

oc-rag-forge · /oc-rag

Tri-agent. Vector-DB decision tree, embedding choice, chunking, hybrid search, and retrieval eval with golden sets and recall@k / nDCG.

oc-agent-forge · /oc-agent

Tri-agent. Claude Agent SDK scaffold, subagent topology, tool-budget design, harness-loop shapes, and eval over task fixtures.

oc-prompt-ops · /oc-prompt

Prompts as artifacts: file-shaped versioning, eval datasets, regression detection. /oc-prompt regress blocks on a score drop.

Cross-skill ripples

oc-app-architect gained an “AI app?” branch in /oc-discover that routes to the four new skills.
oc-stack-forge added vector-DB packs (pgvector, Turbopuffer, Pinecone, Supabase Vectors) to the pack registry.
oc-code-auditor learned a prompt-injection + tool-use AI-safety sweep; opchain published its own dogfooding eval set under oc-prompt-ops.
New GTM surfaces: /ai-recipes, /blog, /for-agencies.

Back-compatible with v1.4. All 22 skills version-bump to 1.5.0; the four new skills ship gated behind their skills.registry.<id>.enabled flags.

What's new

MCP server

A POST /mcp endpoint exposes the catalog, intent routing, the orchestrator protocol, and checkpoints as MCP tools, prompts, and resources — for Codex and any MCP client.

two ways in

Point Codex at the hosted opchain.dev/mcp endpoint, or drop the skills into .codex/skills/ — Codex Agent Skills use the same SKILL.md format.

/oc-* survives

Every /oc-* command is re-exposed as an MCP prompt, so the slash-command flow carries over to clients that surface MCP prompts.

checkpoints anywhere

Session state persists across MCP sessions, so you resume where you left off — the same contract Claude Code uses.

New on /install

Codex / any MCP agent — a fourth install flow with the ~/.codex/config.toml snippet and the .codex/skills drop-in.
local stdio server — an offline mcp/local-server.mjs for air-gapped setups.

Back-compatible with v1.4. The skills are unchanged — only their packaging — so Claude Code installs are untouched. All 18 skills lockstep-bump to 1.4.3.

earlier releases

complete bundlesoc- nameshonest checkpointsdrift detection

The “download all” bundle was dropping each skill's references/, scripts/, and examples/; it now ships full skill trees again. Every skill also gained an oc-<name> alias, the persistence docs were rewritten to the git-tracked checkpoint they actually use, and the validator, spec, and README were reconciled onto one checkpoint schema with drift detection. All 18 skills lockstep-bumped to 1.4.2.

pack registry32 packs5 skills bumped

v1.4 turns oc-stack-forge's coverage from hardcoded prose into a versioned pack registry — one pack.yml per language, framework, mobile platform, or deploy target, validated on every build. /coverage is the user-visible catalog; total coverage grows from 6 stacks in v1.3 to 32 packs.

What's new

Pack registry architecture. scripts/gen-stack-packs.mjs validates every pack on every build.
Hybrid dispatch. oc-deploy-ops reads packs at runtime; oc-api-dev reads them at build time for typed scaffold metadata.
Modern web + enterprise + mobile bulk. elixir / bun / deno / java / csharp / kotlin / php / swift packs; phoenix / remix / sveltekit / solid / spring / dotnet / laravel frameworks; iOS / Android / Flutter / React-Native mobile packs.
Hosting adapters. railway / netlify / heroku / aws-amplify deploy-target packs.

Back-compatible with v1.3. Five skills bump in lockstep to 1.4.0.

oc-release-ops18th skillPM-MCP live

v1.3 makes the v1.2 PM-MCP prose executable end-to-end and ships oc-release-ops — the 18th skill — to automate the scope → /changelog → bump → ship cadence opchain uses for itself.

What's new

The PM-MCP loop is real. Concrete tool-name registry, retry/backoff, idempotency markers, deferred-action queue.
oc-release-ops is the 18th skill. /oc-release plan|draft|bump|announce|ship: reads checkpoints to propose the next semver, drafts the changelog entry, bumps all skill versions atomically.
Platform menu grew. Django + Postgres + Render, Rails + Postgres + Heroku, Go + Fly.io, Rust + Axum + Shuttle.rs.

Back-compatible with v1.2. All 18 skills lockstep at 1.3.0.

PM-MCPLinearJira

The ticket becomes the thread of execution. oc-app-architect, oc-git-ops, oc-deploy-ops, and oc-monitoring-ops all become PM-tool aware.

Back-compatible with v1.1. The PM loop is enrichment, never a hard dependency.

Tri-agent harness across oc-app-architect, oc-code-auditor, oc-integrations-engineer; full-pipeline flow from /oc-discover to /oc-deploy; oc-checkpoint-protocol v1.0 across every skill; static Astro site; first set of six in-action scenarios.

First public cut of the opchain skill catalog as a set of Markdown files installable into Claude Code. No site, no scenarios — just the skills.

What's coming

The one release building right now. Vote to signal priority.

est. Jul 20262 new skillsprotocol bump

v1.6 turns the new AI pipeline from powerful into measurable: per-phase LLM cost attribution, opt-in local usage telemetry, and checkpoint fields for cost, eval scores, and telemetry handles.

What's in scope — vote on what matters most

cost-ops — per-phase LLM cost attribution
New /cost skill: attributes Anthropic spend to each skill phase, adds budget gates to checkpoints, and recommends model-tier routing (Haiku for cheap phases, Opus for spec/audit).
telemetry-ops — opt-in local usage metering
New /telemetry skill: opt-in metering to .checkpoints/usage.sqlite, aggregating anonymized 'skills people actually use' stats that power a public /dashboard.
oc-checkpoint-protocol v1.3 — cost + eval fields
First protocol bump since v1.2: adds cost, eval_scores, and telemetry_handle fields. oc-bug-check and oc-code-auditor start emitting eval scores against a stable rubric, not just pass/fail.

Building next — scope may shift before release. All 24 skills lockstep-bump to 1.6.0.

What's planned

v1.7 is yours to steer; v1.8 and v1.9 group the longer-range work.

theme vote openest. Sep 20261 flagship theme

By the time v1.6 ships, the biggest remaining gap is distribution. v1.7 deliberately promotes one growth play into a flagship theme instead of accreting more skills. The three contenders are below; your vote goes on record now and helps decide the order.

Choose the v1.7 theme

Marketplace + templates
A community skill/pack registry plus opinionated project starters. Every contribution adds breadth at zero core-team cost.
- Public skill and pack listings with install paths, compatibility notes, and maintainer metadata.
- Starter templates that pair a stack-forge pack with the right skill bundle and checkpoint defaults.
- Contribution docs and intake forms that make external submissions reviewable before they appear on opchain.dev.
Agency play
oc-monorepo-ops, multi-project checkpoint scoping, a /for-agencies expansion, and a client-handoff demo scenario.
- A /for-agencies page aimed at studios that run many client builds in parallel.
- Multi-project checkpoint scoping so work can roll up by client, repo, and release train.
- A client handoff demo showing specs, audit trail, deploy state, and what changed since the last review.
Pipeline depth
oc-discovery-ops (JTBD / opportunity trees, upstream of app-architect) and oc-qa-ops, splitting test-pyramid design out of oc-bug-check.
- oc-discovery-ops upstream of app-architect for JTBD, opportunity trees, and problem framing.
- oc-qa-ops for test-pyramid design, contract testing, regression strategy, and release readiness.
- Deeper evaluator rubrics so generated plans include stronger evidence before build and deploy.

Lean, not locked — the final v1.7 theme is chosen after the v1.5 / v1.6 retro.

later planned releases

planned4 items

Make opchain easier to adopt in the places people already work: Claude.ai, editors, discovery, and multi-repo programs.

Claude.ai web skill install
One-click skill install from the opchain site straight into Claude.ai Projects — no file management.
VS Code / Cursor extension
A native sidebar showing checkpoint state, skill shortcuts, and pipeline progress without leaving the editor.
oc-discovery-ops
A JTBD / opportunity-tree skill upstream of app-architect — maps user problems before any code is written.
oc-monorepo-ops
Multi-project checkpoint scoping, shared skill config, and coordinated releases across repos in a monorepo.

Planned — order and scope may shift after the v1.7 theme is chosen.

planned4 items

Deepen the quality, data, compliance, and security layers that larger teams need before they trust the pipeline for serious delivery.

oc-qa-ops
A dedicated test-pyramid design skill: coverage strategy, contract testing, and load-test planning, split out of oc-bug-check.
oc-data-ops
A data-pipeline design skill: ingestion patterns, transformation layers, dbt integration, and observable data contracts.
oc-compliance-ops
SOC 2 / HIPAA / GDPR checklists wired into the pipeline, with audit-ready docs generated at deploy time.
oc-security-hardening
A security-review skill running a full OWASP + threat-model pass before every deploy, separate from oc-code-auditor.

Planned — order and scope may shift after the v1.7 theme is chosen.

missing something?

Request a feature

Lands as a Linear ticket the team triages. We label it community-submitted and reply when it ships if you leave an email. Submissions stay off the public roadmap until a team-member promotes them during triage.

Skill versions are stamped in skills/<name>/SKILL.md under version:; this page rolls them up by release.