Workflow - Command Sequence and Cadence
You ran a Wire command and got nothing useful, or you ran them in the wrong order and now you're not sure what to trust.
Wire has ten commands. They depend on each other in ways that aren't obvious until something goes wrong. Audit reports stale data if you skipped `data` first. News gathering is wasted if you run it before deduplication merges the target page. The sequence isn't a suggestion. But you don't run all ten steps every day, and the right cadence depends on your site. What's your situation right now?
The most common cause of bad audit output is running `audit` before `data`. Audit reads from a local database. If that database is stale or empty, audit reports nothing, or reports numbers from weeks ago. The fix is always the same: run `data` first, then `audit`. But there's a second ordering problem that's less obvious. If you ran `news` before `deduplicate`, you may have gathered content for a page that was about to be merged into another. That work is gone.
The pipeline is a maximum sequence, not a weekly checklist. `data` and `audit` are free and fast. They run as often as you want. The expensive steps, `news` in particular, run on a schedule tied to how fast your content landscape changes. A 20-page local business site and a 500-page SaaS comparison site have almost nothing in common here. Running `news` weekly on a slow-moving site wastes money. Running it monthly on a fast-moving one means your content is always behind.
Most steps are free. `data`, `audit`, `sanitize`, and `build` make no API calls and cost nothing. The expensive step is `news`, which runs 10-20 web searches and evaluations per page. On a 100-page topic, that's a real number before you've changed a single file. `reword` and `refine` cost roughly $0.05-0.10 per page. The cost asymmetry is the point: analysis is free, generation is not. If you're deciding whether to run a step this week, the question is whether the audit flagged anything that justifies the spend.
The audit phase costs zero because it runs locally against a database. No API calls, no tokens. The generation phase costs $0.06 per page because the analysis gives Claude precise instructions rather than open-ended prompts. Precise prompts produce shorter output, which uses fewer tokens. That's the mechanism. The comparison to agency retainers ($5,000-15,000 per month) or freelance consultants ($150-300 per page for audit and rewrite) isn't marketing. It's the same work, different execution cost. The question is whether your team will actually run the pipeline consistently enough to realize that advantage.
Every content command accepts `--dry-run`. Wire writes to `index.md.preview` files instead of overwriting your pages. No changes are saved, no news is archived, no timestamps are updated. You get a diff showing exactly what would change. This matters most before your first `reword` or `refine` run on a section you care about. The output tells you whether Wire's analysis matched your intent before you spend anything. If the preview looks wrong, the problem is usually in the audit data, which means running `data` again is the right next step.
Wire tracks batch progress in `.wire/progress-{command}-{topic}.json`. If a run stops mid-batch, the completed pages are recorded. Running the same command with `--resume` picks up from the last successful page. Failed pages are not marked complete. They retry on resume. The progress file deletes itself when the batch finishes cleanly. If you're seeing a stale progress file after a run that appeared to complete, the batch likely ended on an error rather than a clean finish. Check the last few lines of output before deciding whether to resume or restart.
Wire's batch commands follow a specific sequence. Each step produces data or changes that the next step depends on. Running them out of order wastes API calls or produces suboptimal results. How often you run them depends on your site.
The Full Sequence
# 1. Pull fresh search data
python -m wire.chief data
# 2. Read-only analysis (all topics, or narrow to one)
python -m wire.chief audit
python -m wire.chief audit products
# 3. Resolve keyword cannibalization
python -m wire.chief deduplicate
# 4. Gather industry news
python -m wire.chief news products
# 5. Integrate news into pages
python -m wire.chief refine products
# 6. SEO rewrite based on opportunity score
python -m wire.chief reword products
# 7. Combined analysis + improvement
python -m wire.chief enrich products
# 8. Add internal links to underlinked pages
python -m wire.chief crosslink
# 9. Fix broken internal links
python -m wire.chief sanitize
# 10. Build the site
python -m wire.build --site .
The topic name (e.g. products) is optional for most commands. Without it, Wire scans all topics. With it, Wire focuses on one subdirectory. Use topics to run faster on large sites or to work through one section at a time.
You do not run every step every day. The typical daily workflow is steps 1-2 (data and audit) to see what needs attention. The other steps run as needed.
Why Order Matters
Data before audit. Audit reads from the local database. Without fresh data, audit reports stale information or reports no GSC data at all.
Deduplicate before news. Deduplication merges or differentiates overlapping pages. If you gather news for a page that is about to be merged, that news is wasted effort.
News before refine. Refine integrates pending news files. If there are no news files, refine has nothing to do.
Refine before reword. Refine adds new content from news. Reword optimizes the page's SEO including that new content. If you reword first, the news integration may undo the SEO improvements.
Reword before enrich. Reword handles the top 50% of pages by opportunity score. Enrich handles the remaining actionable pages with a different strategy. Running reword first means enrich does not duplicate effort on high-priority pages.
Cadence by Site Size
How often you run the pipeline depends on how fast your content landscape changes, not on a fixed schedule.
Small sites (20-50 pages)
A local business, a niche authority site, a personal brand. Content changes slowly. GSC data shifts over weeks, not days.
Every 2 weeks: data + audit. Review the output. Most runs will show all + lines and nothing to do.
Monthly: news + refine for topics in fast-moving industries. Skip for evergreen content.
Quarterly: reword pass to capture new keyword opportunities. Enrich pass to strengthen thin pages.
After creating new pages: sanitize + crosslink + build. New pages need internal links immediately.
Medium sites (50-200 pages)
A SaaS comparison site, a consulting firm's knowledge base, a regional service provider.
Weekly: data + audit. At this size, cannibalization and stale content appear regularly.
Every 2 weeks: deduplicate (if overlaps detected), news + refine per topic.
Monthly: reword + enrich + newsweek. Build and deploy.
Large sites (200+ pages)
A multi-topic content operation. At scale, compounding problems (cannibalization, orphan pages, stale content) appear faster than you can manually track them.
Weekly, in order:
# Monday: assess
python -m wire.chief data
python -m wire.chief audit
# Tuesday: resolve conflicts
python -m wire.chief deduplicate products
# Wednesday-Thursday: update content
python -m wire.chief news products
python -m wire.chief refine products
# Friday: optimize + report
python -m wire.chief reword products
python -m wire.chief newsweek
python -m wire.build --site .
Work through one topic per week on large sites. A 500-page site with 5 topics cycles through each topic roughly monthly.
Cost Tracking
Each step has a different cost profile:
| Command | API calls | Typical cost |
|---|---|---|
| data | 0 (GSC API only) | Free |
| audit | 0 | Free |
| deduplicate | 1-2 per overlap pair | $0.05-0.10 per pair |
| news | 10-20 per page | $0.50-1.00 per page |
| refine | 1 per page | $0.05-0.10 per page |
| reword | 1 per page | $0.05-0.10 per page |
| enrich | 1 per page | $0.06 per page |
| crosslink | 1 per page | $0.05 per page |
| sanitize | 0 | Free |
| newsweek | 20-25 total | $3 per report |
| build | 0 | Free |
The most expensive operations are news gathering (many web searches + evaluations) and newsweek reports. The cheapest are data, audit, sanitize, and build, all free.
Dry Run Everything First
Every content command supports --dry-run. Use it to preview changes before committing.
python -m wire.chief reword products --dry-run
In dry-run mode, Wire writes to index.md.preview files and shows a diff. No pages are saved, no news is archived, no timestamps are updated. This is the safest way to verify Wire's output before accepting changes.
Resuming Interrupted Runs
Long batch operations track progress in .wire/progress-{command}-{topic}.json. If a run is interrupted (network error, process killed, rate limit), use --resume to continue from where it stopped.
python -m wire.chief news products --resume
Failed items are not marked as complete. They retry on resume. Progress files clean up automatically when a batch finishes successfully.
The Economics of Automated Content Operations
The workflow sequence is designed around a cost asymmetry that most content teams ignore: analysis is free, generation is expensive. Wire exploits this asymmetry systematically.
The data and audit steps cost nothing. They pull GSC data and run local analysis: database queries, SQL self-joins, statistical comparisons. The output is a complete picture of your site's search performance: which pages cannibalize each other, which pages are dead, where content gaps exist, and which keywords represent untapped demand.
Manual SEO audits produce the same information at dramatically higher cost. An agency charges $2,000-$15,000 per month for ongoing SEO management (WebFX pricing data). An independent SEO consultant charges $150-$300 per page for a detailed audit and rewrite recommendation. Wire produces the audit in seconds at zero cost, then executes the recommendations at $0.06 per page.
The compound effect over time is significant. HubSpot documented their pruning journey: first pass removed 3,000 posts (72% of audited content), producing 106% more organic views. Continued pruning drove a 458% traffic increase. The lesson is not "delete content." The lesson is that systematic content lifecycle management (identify weak pages, merge duplicates, strengthen survivors) produces compounding returns. Wire automates this lifecycle on a weekly cadence.
Monthly cost comparison for a 500-page site:
| Approach | Monthly cost | What you get |
|---|---|---|
| SEO agency retainer | $5,000-15,000 | Monthly audit, recommendations, partial execution |
| Freelance SEO consultant | $3,000-7,500 | Audit + rewrite for 20-50 pages per month |
| Wire automated workflow | $30-50 | Full audit, all pages enriched, news integrated, weekly reports |
The 100x-250x cost advantage is not marketing. It is arithmetic. The analysis phase (audit, overlap detection, keyword routing) costs zero because it runs locally. The generation phase costs $0.06 per page because Claude receives precise instructions from the analysis, not open-ended prompts. Precise prompts produce shorter, more accurate output, which uses fewer tokens.
When to Skip Steps
Not every step runs every week. The workflow is a maximum sequence, not a mandatory checklist.
Skip deduplicate when the audit shows no overlap pairs above the minimum threshold. This is common after the first few weeks of running Wire. Once overlaps are resolved, new ones appear slowly.
Skip news when all topics are within their freshness intervals. If products were updated 10 days ago and the interval is 21 days, there is nothing to gather yet.
Skip reword when the audit shows no keywords scoring above the opportunity threshold. This happens on well-optimized sites where most pages already target the right keywords.
Never skip data and audit. These are free. They take seconds. Skipping them means operating on stale information.