Claude Code
Hands-on articles for the Claude Code CLI — installation, CLAUDE.md design, subagents, hooks, CI integration, and fixes for common errors.
My MCP Timeout Was Being Ignored, and Every Call Died at Exactly 60 Seconds — Reclaiming Per-Server request_timeout_ms
A longer MCP tool call kept dying at exactly 60 seconds, ignoring the wait I had set. The cause: a per-server request_timeout_ms in .mcp.json that was never read, silently falling back to the default. Here is the correct placement after the fix, how to back the value out from a tool's response profile, and how to verify the cutoff yourself — with working code.
Carrying Decisions Across Compaction with PreCompact and SessionEnd Hooks
Auto-compaction does not delete your conversation. It deletes the reasons behind it. Here is a working PreCompact / SessionEnd / SessionStart hook pipeline that rescues decisions to disk and hands them to the next session, with real code and measurements.
Is the Draft That Passed the Gate the Same One You Published?
In unattended pipelines, the file your quality gate inspected and the file you actually publish can quietly diverge. Here is a digest-bound gate receipt design, with working code and measured results from 180 days of running it.
Claude Code and Cursor: Stop Trusting Benchmarks, Measure on Your Own Repo
A comparison of Claude Code and Cursor built on three things you can verify: design philosophy, agent capabilities, and how each one bills you. Includes a runnable procedure for measuring time and token cost on your own repository, plus how to draw a boundary when running both.
Auditing Your Own Code for Required Reason API Declarations with Claude Code
Required reason codes in PrivacyInfo.xcprivacy apply to your own code, not just third-party SDKs. After a wallpaper app of mine was rejected, here is the Claude Code workflow I use to scan Swift sources and match APIs to reason codes before submission.
I Could Detect Failures — Then the Alerts Grew So Loud I Stopped Noticing
The moment I could detect silent job failures, my phone started buzzing too often to be useful. Here is how I collapsed alerts by action rather than event, added hysteresis and quiet hours, and built a three-step escalation so only the pages worth waking me survive.
My background session sat at running all night — adding heartbeats to the agents view
The Claude Code agents view finally lets you see every background session at once, but a running badge is not proof of progress. Here is the external heartbeat layer I built to catch a silently stalled session in minutes instead of the next morning, with real numbers and the traps I hit.
Which Nightly Job Wrote This Commit? Threading a Correlation Key Through Claude Code's Readable Session Names
When you run unattended nightly jobs across several repositories, you lose track of which session produced which commit. Here is how I redesigned Claude Code's readable session names into a correlation key that ties commits, logs, and sessions into a single thread — with real numbers.
I Was Starting the Ad SDK Before the Consent Dialog — Fixing ATT and AdMob Ordering with Claude Code
Starting the ad SDK at launch initializes it before ATT consent, so the IDFA is all zeros and only your measurement goes thin while fill rate stays fine. Here is how I traced the scattered init paths with Claude Code and reshaped them to start ads only after ATT resolves.
Rolling Out Trusted Devices for a Small Team: Enrollment, Preflight, and Rotation
How to introduce Team/Enterprise Trusted Devices for a 2-5 person team: device enrollment, an unattended-run preflight gate, and closing the gaps that appear during device rotation and offboarding.
When to Use Claude Code's Native 1M Context — and When Not To: A Cost-Based Rule
With Sonnet 5 as the default, Claude Code now handles a native 1M-token context. A big window is convenient, but every token you park in it is billed again each turn. Should you load the whole repo, or feed slices? Here is an estimable token model and a decision rule that gives a concrete answer per situation, with working code and the traps to avoid.
A 1M Context Window Is the New Default — So I Built an Admission Policy Instead of Filling It
Sonnet 5 is now the Claude Code default and native 1M context is standard. The hard errors disappeared, but a quieter kind of degradation took their place. Here is how I made it visible with a probe, plus an admission policy and an effective-token-cost view — with working code and my own measurements.
Keep the Extra Capacity Out of Your Baseline — Burning Backlog During the Time-Boxed +50% Weekly Limit
Claude Code's weekly limits are raised 50% until July 13. A design for spending the temporary headroom only on finite backlog work: an expiry-aware burst queue, a dual-lane ledger, and a single ratio that tells you whether your baseline quietly grew.
Five Minutes of Silence, and Something Retries on Your Behalf — Rethinking Retry Ownership After the Streaming Idle Watchdog Became a Default
Claude Code's streaming idle watchdog is now on by default, quietly adding another retrying layer to your stack. This article inventories the four layers (SDK, wrapper, watchdog, scheduler), computes worst-case attempt amplification, and shows how to collapse retry ownership into a single layer.
When a Claude Code Refactor Passes Every Test but Behaves Differently in Production — Catching Silent Contract Drift with a Behavior Diff Harness
Hand Claude Code a large refactor and your tests can stay green while production behavior quietly shifts. Here is how I record exception channels, log shape, init order, and return values as a signature, then diff them per commit to catch contract drift before it ships.
Which Model Ran Last Night's Unattended Session? Building Model Attribution and Default-Drift Detection After the Sonnet 5 Switch
Claude Code's default model switched to Sonnet 5, and unpinned headless runs changed models silently. Here is a working design for extracting the actual model from run output, appending an atomic run record, and deciding per task lineage whether to pin or follow the default.
Don't Accept an Agent's Numbers and Citations As-Is — A Verification Gate Built on a Dedicated Auditor Subagent
A design that verifies every number and citation in an agent-generated summary using a separate subagent before accepting it — with working TypeScript for deterministic recomputation and fail-closed source matching.
My Claude Code Hooks Stopped Firing After an Update — the Hyphenated Matcher Exact-Match Change in v2.1.195
In Claude Code v2.1.195, hook matchers containing a hyphen switched from partial match to exact match, silently disabling an existing PreToolUse hook. Here is how I isolated the cause and how to write matchers that won't break.
Fixing Blurry Wallpapers on New iPhones with Claude Code: Safely Growing a Per-Device Resolution Map
Why wallpapers go blurry or letterboxed on brand-new iPhones, and how to collapse scattered device branches into a single source of truth you can extend in one line — walked through as a real Claude Code refactor with before/after code.
Borrowing the Trusted Devices Idea for a Solo Setup: Pinning Automated Runs to Devices You Approved
The Trusted Devices feature that landed in Claude Code on June 28, 2026 is for Team and Enterprise. You can't use the feature on a solo plan, but you can borrow the idea. Here is how to identify a device in a way that doesn't break, and stop any automated run that starts from a device you never approved — with working code and the traps to avoid.
When You Fan Out Streaming Sessions, Your Laptop's CPU Gives Out First — An Adaptive Throttle That Caps Concurrency by Measured Load
Even with lighter streaming, fanning out many sessions on one machine saturates the host CPU before anything else. Here is why a fixed semaphore fails, plus a working adaptive gate that raises and lowers concurrency from measured CPU.
Stop Leaving a Static API Key in Your Unattended Jobs — Move to Short-Lived WIF Credentials
Claude Code is moving from static API keys toward short-lived, scoped credentials via WIF (Workload Identity Federation). Here is how to translate that idea to a small unattended pipeline so a leaked key has a much smaller blast radius — with working code and the failure modes to watch.
When an OAuth Token Expires, Your Unattended Run Has Nowhere to Go — A Token-Lifecycle Design That Keeps Remote MCP Alive
Remote MCP connectors are authorized via OAuth, but access tokens are short-lived. Interactive sessions can re-authorize in a browser; an unattended scheduled run has nobody to click the dialog. Here is a token-lifecycle design that owns expiry and refreshes ahead of time.
Will It Stay Light When You Run It Unattended? Observing and Capping Claude Code's Long-Session Memory
How to keep long, unattended Claude Code sessions from slowly getting heavier — with a tiny ps-based RSS sampler, a rolling-baseline watchdog, and session segmentation, shown with working scripts and a before/after comparison.
When You've Gone Five Steps in the Wrong Direction: Rewinding Conversation and Code with Claude Code's /rewind
Claude Code's /rewind is a safety net that returns both conversation and code to an earlier checkpoint. Here is how it differs from git, what it restores, and the pitfalls that bite in automated runs.
We Collected Plenty of Claude Code Usage Data — Then Budgeting Still Didn't Work. Field Notes on Cost Attribution and Idle Seats
The Claude Code Analytics API gives you data, but data alone doesn't run a budget. Here are field notes on turning raw usage logs into cost attribution, idle-seat detection, and alerts that don't cry wolf — with working code and the thresholds we actually use.
The Day a Non-Responding MCP Call Swallowed an Entire Unattended Run — Owning the Stop With Your Own Deadline
When a remote MCP tool call stops responding, an unattended scheduled run just keeps waiting. Instead of leaving the cutoff entirely to the platform, here is how I designed my own deadline and a per-connector circuit breaker to own the stop — with working code.
Higher Rate Limits Don't Mean Tighter Schedules — Spend the Headroom on 429 Recovery
When Claude Code's rate limits went up, the instinct was to pack the schedule tighter. Here's why I did the opposite and routed the new headroom into retry budget instead — a pacing note for unattended pipelines.
Your Sandbox Can Run the Code but Shouldn't Read Your Credentials — Shrinking the Secret-Read Surface with sandbox.credentials
Claude Code's sandbox can still read ~/.aws/credentials and token env vars by default. Using sandbox.credentials (v2.1.187+), here is how I tightened the secret-read surface of unattended runs at the OS level, with config and verification you can reuse.
Productionizing a Claude Design Prototype — Single Source, CI, and OGP Auto-Generation
Turn a Claude Design prototype into something that survives production with Claude Code. The call to keep the generated runtime as your foundation, separating logic with a mixin, a single-source data design around a ledger CSV, and CI auto-updates with real-browser OGP capture — implementation included.
I Watched an Agent Try to Fix a File It Had Already Fixed — Stale Shallow Clones and Refreshing Before You Decide
An unattended agent tried to re-fix a file it had already fixed. The cause was a days-old shallow clone it kept reading. Here is how to detect that staleness numerically and re-clone only before decisions.
Working Between Claude Design and Claude Code — Splitting Diverge and Converge
Rough design in Claude Design, fine detail in Claude Code. Now that the two live close together in the desktop app, here is how to run them as a divide-of-labor between diverging and converging — bridges like Link Local code and Send to included.
When Claude Code Still Writes Stale Code With Context7 Installed — Verifying the Injection Actually Worked
You installed Context7 MCP, yet Claude returns code against a deprecated API. Most of the time the documentation injection silently no-ops. Here are field notes on a hook that detects misses, pinning doc versions, and a harness that checks generated code every time.
Keep MCP Connector Authorization in One Place — A Solo Dev Design That Survives Growing Integrations
When Claude chat, Claude Code, and Cowork each configure the same MCP connector separately, their authorization drifts apart and breaks silently. Here is how to borrow the managed-connector idea of 'provision once, reuse everywhere' as an indie developer.
Handing Claude Design Mockups Straight to Claude Code: Folding the Design-to-Code Loop
The June 17 Claude Design update added codebase-aware generation. Here's how to make your tokens the single source of truth, hand mockups to Claude Code, and collapse the design-to-code round trip — with code you can copy.
Noticing From the Outside When a Scheduled Job Quietly Did Nothing
exit 0, but zero output. How to catch a silent no-op not from the job's own log but from an external heartbeat ledger and ground truth, written from running several sites on a nightly schedule as an indie developer.
An Article My Gate Rejected Got Published — The Cost of Chaining the Quality Gate and git push in One Call
In an unattended publishing pipeline, an article my quality gate had rejected went live anyway. The cause was chaining the gate and git push into a single shell call. Here is how the exit code gets swallowed, and a two-phase publish-marker design that refuses to push until every gate has demonstrably passed.
Claude Code Adds /cd — Carrying Your Warm Cache Across Repositories
Claude Code's new /cd moves a running session to another working directory without rebuilding the prompt cache. Here are the design calls and pitfalls when you sweep across several repositories in one sitting.
Moving Cleanup and Logging into a SessionEnd Hook
How to use Claude Code's new post-session hook to automate temp-file cleanup and log writing after a session ends, with real examples from a pipeline that processes several repositories in sequence.
Give an Unattended Agent Only the MCP Tools It Needs — Enforcing a Deny-by-Default Policy
An unattended Claude Code agent can't lean on a permission prompt, so whatever a tool can reach becomes the blast radius. Here's how to lock MCP servers and tools down to deny-by-default and hand back only what the job needs, with managed-settings.json examples.