SAFASTUDIOS

Safa Global · Claude Code

Claude Opus 4.8

4.8 + ultracode + Workflows. The release that turns Claude Code from a turn-by-turn pair-programmer into a background orchestrator of hundreds of agents, and what it means for how Safa ships work.

Prepared 2026-05-28

Listen · executive audio briefing

Executive audio briefing. Two hosts, about 22 minutes.


Download audio (.m4a)

The takeaway

Opus 4.8 is not mainly a "smarter model" story. The real shift is dynamic workflows: Claude now writes a script that orchestrates dozens to hundreds of subagents in the background, with agents adversarially checking each other, while your session stays free. Work scoped in quarters can finish in days.

ultracode (/effort ultracode) is the easy button: maximum reasoning effort plus automatic workflow orchestration, so Claude decides when a task deserves an agent swarm. Use it for codebase-wide audits and large migrations; keep routine work on /effort high - workflows cost meaningfully more tokens.

01 What changed in Opus 4.8

Anthropic's most capable generally-available model, released 28 May 2026. Built for professional software engineering, complex agentic work, and high-stakes enterprise tasks - at the same token price as 4.7.

LeverDetail
Standard price$5 / M input · $25 / M output (unchanged from 4.7)
Fast mode$10 / M input · $50 / M output - 3× cheaper than on prior models
Caching / batchUp to 90% off with prompt caching · 50% off with batch
Effort levelshigh (default) · xhigh · max

02 Dynamic workflows: the engine

A dynamic workflow is a JavaScript script Claude writes that orchestrates subagents at scale. A runtime executes it in the background while your chat session stays responsive, and only the final answer lands back in Claude's context.

The key mental shift is who holds the plan. With subagents and skills, Claude is the orchestrator and every intermediate result fills its context. A workflow moves the loop, the branching, and the intermediate results into code - so it can apply a repeatable quality pattern: independent agents draft a plan from several angles, or adversarially review each other's findings, before anything is reported.

SubagentsSkillsWorkflows
What it isA worker Claude spawnsInstructions Claude followsA script the runtime runs
Who plansClaude, turn by turnClaude, per promptThe script
Results live inClaude's contextClaude's contextScript variables
ScaleA few per turnSameDozens to hundreds
If interruptedRestarts the turnRestarts the turnResumable

Runtime limits worth knowing

Up to 16 concurrent agents (fewer on low-core machines), a hard cap of 1,000 agents per run, no mid-run user input (run each sign-off stage as its own workflow), and resume works only within the same Claude Code session.

Proof point: Bun was ported from Zig to Rust - ~750,000 lines, 99.8% of the existing test suite passing - in eleven days using dynamic workflows, with two reviewer agents per file.

03 ultracode: the easy button

ultracode = xhigh reasoning effort + automatic workflow orchestration. Turn it on and Claude plans a workflow for every substantive task itself, instead of waiting for you to ask.

Enable/effort ultracode - lasts the current session, resets on a new one
Drop back/effort high when you return to routine work
BehaviourOne request can become several workflows in a row: understand the code → make the change → verify it
The costEvery task uses more tokens and takes longer. Only available on models that support xhigh effort

Think of the three gears: /effort high for everyday work, the workflow keyword for a single big task on demand, and /effort ultracode when you're heads-down on something large and want Claude to escalate on its own.

04 How to drive it

Three ways to launch a workflow

Watch and control runs · /workflows

Runs happen in the background; /workflows opens the progress view - phases with agent counts, token totals, and elapsed time.

KeyAction
pPause / resume the run
xStop an agent, or the whole workflow
rRestart a running agent
sSave the run's script as a reusable /command

Save to .claude/workflows/ (shared with the repo) or ~/.claude/workflows/ (personal, every project). A saved workflow becomes /<name> in future sessions - the orchestration itself becomes repeatable, not just the prompt.

Setup gate

Research preview. Needs Claude Code v2.1.154+. On by default for Max and Team; turn on from the Dynamic workflows row in /config on Pro; Enterprise needs admin activation. Works in CLI, Desktop, IDE extensions, claude -p, and the Agent SDK.

05 When to use it, and when not

Reach for a workflowStay in normal chat
Codebase-wide audits (security, dead code, missing auth)A single-file edit or quick fix
Large migrations: framework swaps, API deprecations, language ports across hundreds of filesA question you can answer in one turn
High-stakes work where a wrong answer is costly and you want adversarial verificationAnything one conversation already handles well
Research that must cross-check many sources against each otherExploratory back-and-forth where you steer each step

The cost is real

A run spawns many agents, so it can use meaningfully more tokens than doing the same task in conversation, and it counts toward your plan's usage and rate limits. Start scoped to learn the usage pattern. Check /model before a large run, and ask Claude to route stages that don't need the strongest model to a smaller one.

06 Deploying it across Safa

Where ultracode and workflows earn their token cost first, given our stack:

  1. Aquiii security sweep. Run a workflow to audit every API route under ~/aquiii-webapp/src for missing auth checks, then verify the pending Shopify token rotation is fully propagated. Independent agents per route, adversarially reviewed.
  2. safa-ops standardization. A migration workflow to normalize all 13 Skills' SKILL.md frontmatter and cross-links in one run, instead of editing them one by one.
  3. Save a /branch-review workflow. Build the review once on a feature branch, press s, and reuse the same multi-agent orchestration on every branch from then on.
  4. Default posture. Keep team members on /effort high day-to-day; reserve /effort ultracode for migrations and audits where the extra tokens buy verified correctness.
  5. Govern the spend. Because workflows multiply token use, set the expectation that ultracode is a deliberate choice for big tasks - track it like any other infra cost.