EVC

April 5, 2026 · View on GitHub

The agent workspace for marketing operators.

42 commands. 12 hooks. 3 modes. 4 starters. One setup.sh.

An opinionated marketing agent system for Claude Code. Clone it, configure it, run /project:monday to start your week.

Visual overview →

What this is

EVC is a folder. Inside it:

evc/
├── _templates/                 # Source of truth (tracked in git)
│   ├── commands/               # 42 command prompts with {{TOKENS}}
│   ├── hooks/                  # 12 shell scripts that fire on events
│   ├── contexts/               # 3 mode files (content/build/research)
│   ├── staging/                # Shared staging stylesheet
│   ├── SOUL.md                 # 7 operating principles
│   └── CLAUDE.md               # Top-level agent instructions
│
├── .claude/                    # Rendered output (gitignored)
│   ├── commands/               # Your 42 rendered commands
│   ├── hooks/                  # Your 12 rendered hooks
│   └── contexts/               # Your 3 rendered modes
│
├── brand/                      # Your brand brain
│   ├── canon-rules.json        # Banned phrases, USPs, required language
│   └── canon-history/          # Auto-maintained snapshots + CHANGELOG
│
├── content-engine/             # Working memory
│   ├── memory/                 # Lessons, learning log, visual log
│   ├── output/                 # Weekly posts, blog drafts, reports
│   └── calendar/               # Weekly briefs + reviews
│
├── staging/                    # Browser previews before publish
├── scripts/                    # Validation, secret scan, staging helpers
├── starters/                   # 4 industry configs (web3/saas/ecom/generic)
├── config.env.example          # Template — copy to config.env
└── setup.sh                    # One command to render everything

Every command is a markdown file. Every hook is a shell script. The workspace is just files — fork it, read it, change it.

Quick start

git clone https://github.com/SaigonXIII/evc.git
cd evc
./setup.sh

Setup takes 2 minutes:

Pick your industry (Web3, SaaS, E-commerce, Generic)
Fill in 5 required variables
Done — 42 commands installed, 12 hooks wired

Then open Claude Code in the directory:

/project:start

Commands

Chains (the point of entry)

Command	What it does
`/project:monday`	Start the week: comms + review + intel + plan + brief (5-in-1)
`/project:friday`	Close the week: review + digest + cleanup + memory (4-in-1)

Command	What it does
`/project:intel-scan`	Weekly research — competitors, trends, algorithm changes
`/project:performance-review`	Pull X metrics, rank posts, extract winning patterns
`/project:content-plan`	Build weekly brief with 5-day calendar
`/project:content [day]`	Produce one day's post + visual
`/project:content-week`	Batch produce all 5 days
`/project:crosspost`	Adapt for X, LinkedIn, Threads
`/project:post-today`	Publish + auto-reply with link
`/project:reply-monitor`	Scan mentions, draft canon-aligned replies

Blog Engine (long-form)

Command	What it does
`/project:blog-plan [topic]`	Research + outline with visual map
`/project:blog-draft [slug]`	Write 1,200–2,000 word semantic HTML
`/project:blog-qa [slug]`	8-check quality pipeline with auto-revision
`/project:blog-assets [slug]$	\text{Build} \text{visual} \text{templates}, \text{export} \text{PNGs} \text{at} 1200 \times 675
$/project:blog-publish [slug]`	Push to CMS + sync components
`/project:sync-blogs`	Sync CMS data back to local components
`/project:repurpose [slug]`	Fan one blog into X thread, LinkedIn, newsletter, quote cards

QA & Review

Command	What it does
`/project:content-qa`	6-check pipeline + brand voice score (0–50)
`/project:content-review`	Audit copy against brand canon
`/project:stop-slop`	Detect and remove AI writing patterns
`/project:copy-review`	Brand voice + legal guardrail check
`/project:site-audit`	Scan live site for brand drift (returns node IDs)
`/project:compliance-check`	Jurisdiction-aware compliance (US/EU/UK)
`/project:reference-capture`	Screenshot live site before building visuals

Comms

Command	What it does
`/project:comms-scan`	Unified inbox triage (Gmail + X + Linear)
`/project:slack-comms`	Read, post, summarize Slack channels
`/project:community-harvest`	Convert community questions into content topics

Memory & Productivity

Command	What it does
`/project:save-session`	Save full session state for continuity
`/project:resume-session`	Load last session and continue
`/project:deep-research`	Multi-source research with cited reports
`/project:lesson-capture`	Record what worked/failed for future sessions
`/project:canon-diff [since]`	View canon change history with optional restore

Setup

Command	What it does
`/project:start`	First-time onboarding wizard
`/project:help`	Full command index grouped by use case
`/project:setup-canon`	Interactive brand rules builder
`/project:upgrade`	Pull latest + re-render templates
`/project:security-audit`	Secret scan + permissions + audit log review

Staging & Pipelines

Command	What it does
`/project:stage [type] [name]`	Build staging HTML (blog, week, or asset)
`/project:dashboards`	Build master dashboards (commands, canon, design system)
`/project:export-clean [file]`	Strip internal version drawer for clean publish
`/project:content-pipeline`	Full Content Engine flow diagram
`/project:blog-pipeline`	Full Blog Engine flow diagram

Pipelines

Content Engine (Mon→Fri)

/intel-scan → /performance-review → /content-plan → [You review]
  → /content-week → /content-qa → [You review] → /post-today

Blog Engine (per article)

/blog-plan → [You review] → /blog-draft → /blog-qa → [You review]
  → /blog-assets → /stage → [Browser review] → /blog-publish → /repurpose

Human gates at every decision point. The system drafts, you approve.

The brand brain

brand/canon-rules.json is the single source of truth:

{
  "banned_phrases": [{"phrase": "...", "reason": "..."}],
  "framing_red_flags": ["best in class", "revolutionary", "..."],
  "required_language": {"product_name": "...", "company_anchor": "..."},
  "usps": ["...", "..."],
  "defunct_partners": ["OldBrand"],
  "live_partners": ["PartnerA", "PartnerB"],
  "compliance_rules": {"US": {...}, "EU": {...}, "UK": {...}}
}

Every command reads it. The canon-guardrail hook blocks violations before they ship. The canon-changelog hook snapshots every edit to brand/canon-history/. Run /project:canon-diff to see what changed and when.

Hooks

12 shell scripts that fire on Claude Code events. You don't call them — they run automatically.

Hook	Event	What it does
`canon-guardrail`	PreToolUse	Blocks banned phrases in outbound content
`check-reference`	PreToolUse	Blocks visual builds without a live-site screenshot
`block-no-verify`	PreToolUse	Blocks `git commit --no-verify`
`commit-quality`	PreToolUse	Blocks secrets and debugger code in staged files
`suggest-compact`	PreToolUse	Suggests `/compact` after long sessions
`canon-changelog`	Stop	Snapshots canon edits + appends CHANGELOG entry
`session-end`	Stop	Auto-saves session state
`action-audit`	Stop	Logs every external action to audit.log
`cost-tracker`	Stop	Logs token usage and cost estimates
`desktop-notify`	Stop	macOS notification when a long task finishes
`session-start`	SessionStart	Loads last session state, memory, pending tasks
`pre-compact`	PreCompact	Saves context before compaction

Configuration

Required (5 variables)

Variable	Example
`COMPANY_NAME`	"Acme Corp"
`WEBSITE_URL`	"acme.com"
`SOCIAL_HANDLE_X`	"@acmecorp"
`ANCHOR_STATEMENT`	"Acme does X so Y can Z"
`BRAND_PRIMARY_COLOR`	"#00c891"

Industry starters

Pre-filled configs in starters/:

web3.env — crypto compliance, community-first, Discord
saas.env — LinkedIn-heavy, case studies, product-led
ecommerce.env — product launches, seasonal cadence, conversion
generic.env — baseline for anything else

See config.env.example for the full variable list including CMS IDs, Linear prefix, compliance jurisdictions, and credential paths.

Memory

EVC gets smarter the longer you use it:

QA failures → lessons. Failed content auto-appends to content-engine/memory/lessons.md. Ships with 14 pre-loaded.
Performance → planning. /performance-review writes winning patterns to learning-log.md. /content-plan reads it before building next week's brief.
Session continuity. session-end hook saves state on every stop. session-start loads it. No manual save required.
Canon freshness. validate.sh warns if brand rules are over 30 days old.

Security

.secrets/ — chmod 700, owner-only. Never committed.
config.env — chmod 600. References token files, not inline keys.
scripts/secret-scan.sh — Scans for leaked API key patterns. Runs on setup.
Action audit log — every external action logged append-only to .claude/audit.log.
Nothing auto-sends. Every post, message, and CMS push requires explicit approval.

Extending

Add a command

# 1. Write the prompt
vim _templates/commands/my-command.md

# 2. Render
./setup.sh

# 3. Use it
/project:my-command

Add a hook

# 1. Write the script
vim _templates/hooks/my-hook.sh && chmod +x _templates/hooks/my-hook.sh

# 2. Wire it in setup.sh → settings.json

# 3. Render + validate
./setup.sh && ./scripts/validate.sh

Every command is a markdown file. Every hook is a shell script. If you can write a prompt, you can extend EVC.

Credits

Built by SaigonXIII. Battle-tested internally before open-sourcing.

Inspired by Everything Claude Code — the community-built power-user kit for developers. EVC is the same idea, reshaped for marketing.

Open source under the MIT License — fork it, rename it, make it yours.