A command that runs multiple automated checks on a software project before continuous integration (CI), the system that tests code after changes. It also creates a report of issues.

Use it after implementation to check code, builds, migrations, containers, dependencies, bundles, and— for larger projects—contracts and load behavior.

It gathers checks for performance, security, accessibility, dependencies, end-to-end behavior, and other common problems in one run, retrying temporary failures.

optimize — Command by marcusgoll

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/marcusgoll/spec-flow/optimize

Clone the repo

git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 6,522 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00038	$0.06522
Opus 5	$0.00019	$0.03261
Sonnet 5	$0.00008	$0.01304
Haiku 4.5	$0.00004	$0.00652

Measured 2d ago against content hash 3ecf2c037cb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/phases/optimize.md · 812 lines

How it starts

The opening of the file, as written. The whole thing — 812 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/optimize — Quality Gates Runner (Thin Wrapper)

v11.0 Architecture: This command spawns the isolated optimize-phase-agent via Task(). All quality gate logic runs in isolated context.

Active Feature: !ls -td specs/[0-9]*-* 2>/dev/null | head -1 || echo "none"

Interaction State: !cat specs/*/interaction-state.yaml 2>/dev/null | head -10 || echo "none"

Architecture (v11.0 - Phase Isolation):

/optimize → Task(optimize-phase-agent) → optimization-report.md

Agent responsibilities:

Run 15 parallel quality checks
Auto-retry transient failures (2-3 times)
Generate optimization-report.md
Return blocking issues or completion status

Quality Gates (15 checks, expandable to 18 for epics): 1-7: Core (performance, security, a11y, code review, migrations, docker, E2E) 8-15: Pre-CI (licenses, env vars, circular deps, dead code, dockerfile, deps, bundle, health) 16-18: Epic-only (contracts, load testing, migration integrity)

Auto-Retry Logic:

Transient failures auto-retry with progressive delays
Critical failures (security, breaking changes) block immediately

Prerequisites: /implement phase complete

Workflow position: spec → clarify → plan → tasks → implement → optimize → ship

Legacy Context (for agent reference)

<legacy_context> Workflow Detection: Auto-detected via workspace files, branch pattern, or state.yaml

Current phase: Auto-detected from ${BASE_DIR}/*/state.yaml

Implementation status: Auto-detected from ${BASE_DIR}/*/state.yaml

Quality targets: Auto-detected from ${BASE_DIR}/*/plan.md </legacy_context>

Step 0: WORKFLOW DETECTION

Detect workflow using centralized skill (see .claude/skills/workflow-detection/SKILL.md):

Run detection: bash .spec-flow/scripts/utils/detect-workflow-paths.sh
Parse JSON: Extract type, base_dir, slug from output
If detection fails: Use default (feature workflow with 6 gates)
Set gate count:
- Feature: 6 core gates
- Epic: 10 gates (core + enhanced)
Set WORKFLOW_STATE="${BASE_DIR}/${SLUG}/state.yaml"

Read the full file on GitHub · 812 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 812 lines · 38 tokens per session scan A 3ecf2c037cb3

Subscribe to this mod's changes

optimize is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 6,522 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DevOps and cloud Productivity Testing ai-agents ai-assisted-development ai-workflows automation bash claude

optimize

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/optimize — Quality Gates Runner (Thin Wrapper)

Legacy Context (for agent reference)

Step 0: WORKFLOW DETECTION

What this file has done since we first saw it

Other commands, from other repositories

quick-fix

review

usage-add

pi-code-review

milestone-list

setup