CLAUDE LABJP
MODEL — Claude Fable 5.1 and Claude Mythos 5.1 landed on September 1. They are the same underlying model; only the strength of the safeguards differsPRICING — Per-token rates hold at $10/$50 per MTok. What changed is cache reads, cut 75% to $0.25 per MTokCOST — How much that saves depends on your workload: roughly 25% for typical use, up to about 45% for context-heavy agentic work. Worth measuring your own split before quoting a numberBENCH — Terminal-Bench-Science 0.1 climbs from 24.7% on Fable 5 to 52.6%. Anthropic also states a standard error of 3.5-4.5 points, which is worth remembering before reading small gaps as realSAFEGUARDS — Sharper cyber safeguards cut interventions in Claude Code sessions by roughly 60% on average. Finding vulnerabilities is now allowed; developing exploits still is notAPI — New API accounts created from today can no longer edit prior context while preserving Claude's thinking transcript. It is an anti-distillation measure, and existing accounts are unaffected for nowMODEL — Claude Fable 5.1 and Claude Mythos 5.1 landed on September 1. They are the same underlying model; only the strength of the safeguards differsPRICING — Per-token rates hold at $10/$50 per MTok. What changed is cache reads, cut 75% to $0.25 per MTokCOST — How much that saves depends on your workload: roughly 25% for typical use, up to about 45% for context-heavy agentic work. Worth measuring your own split before quoting a numberBENCH — Terminal-Bench-Science 0.1 climbs from 24.7% on Fable 5 to 52.6%. Anthropic also states a standard error of 3.5-4.5 points, which is worth remembering before reading small gaps as realSAFEGUARDS — Sharper cyber safeguards cut interventions in Claude Code sessions by roughly 60% on average. Finding vulnerabilities is now allowed; developing exploits still is notAPI — New API accounts created from today can no longer edit prior context while preserving Claude's thinking transcript. It is an anti-distillation measure, and existing accounts are unaffected for now
ARTICLES

All Articles

All (845) Claude AI (136) Claude Code (361) Cowork (57) API & SDK (291)
API & SDK/2026-09-02Intermediate

The 400 that rejects a thinking block, and finding the edit that caused it

On Claude Fable 5.1, editing the system prompt, tools, or earlier messages before a thinking block makes the request fail with a 400. Here is how to check whether your own agent loop does that in a single request, and how to move a rebuilt system prompt and client-side trimming to patterns that leave the prefix untouched.

Claude Code/2026-09-02Intermediate

Two hooks that record every model switch and stop the ones you never agreed to

Build a PostModelSwitch hook that logs every model change and a PreModelSwitch hook that blocks unapproved switches during unattended runs. Complete scripts, measured timings, and the reason the two jobs must stay separate.

Claude Code/2026-09-01Intermediate

Drop the quotes on a heredoc and the prices in your log quietly change

An unquoted heredoc runs the variables and backticks inside its body. Here are the four ways my log got rewritten, how the three quoting forms compare, a safe placeholder-and-sed pattern, and a small script for auditing what you already have.

Claude Code/2026-09-01Advanced

Once I passed a dozen MCP servers, I stopped trusting the startup list

Only some of the servers that say connection failed at startup are ones you can actually fix. Here is a probe that separates no-response, launch failure, and protocol rejection, measured across a 14-server fleet where sequential 22.03s became parallel 5.09s, and where trimming the deadline quietly turned healthy servers into failures.

Claude Code/2026-08-31Beginner

The Same Announcement Reads as '+25%' and as 'a 17% Cut' — Checking the Math on Claude Code's September 14 Weekly Limit Change

From September 14, Claude Code's weekly limit becomes a permanent +25% over the pre-promo baseline. Here is why +25% and a 17% cut are the same change, and how to check your own exposure with /usage and a status line script.

Claude Code/2026-08-31Intermediate

Half of My Scheduled Runs Vanished Without a Single Error

A batch job set to run twice a day was only firing once. No errors, no failure alerts. Here is how to expand your own schedule, count expected runs, and reconcile them against execution records to catch silent misses.

Claude Code/2026-08-30Intermediate

Your Config Asks for effort xhigh With Thinking Off, and It Now Quietly Runs at high

Disabling thinking while asking for effort xhigh or max returns a 400. That failure now degrades silently to high instead, so here is a small preflight that catches the mismatch before you send the request.

API & SDK/2026-08-30Advanced

Read the Catalog Your CLI Already Ships Before Bulk-Replacing Model IDs

A newer generation makes older model IDs look stale. Here is how to pull the catalog embedded in your installed binary, sort every reference into matched, date-mismatched, and malformed, and stop the replacement that would break working IDs.

Claude AI/2026-08-29Beginner

The 30-Day Session Cleanup Is Fixed, and It Made Me Rethink Where I Keep Records

Claude Desktop and Cowork sessions were quietly disappearing after 30 days until v2.1.248 fixed it. Here is how to check your own setup, what the new setting actually caps, and a small journal script that keeps one line per run outside the session.

Cowork/2026-08-29Advanced

The lock I left in a shared folder shut out every run after the first

A cloud-synced connected folder allows create, append, and rename, but refuses delete. Putting a single-instance lock there quietly disabled every unattended run after the first. Measurements for three lock styles, plus an implementation that picks a safe location.

Claude Code/2026-08-28Beginner

A small script that catches invisible characters in plugin names before you install

Control characters and zero-width characters hiding in plugin or skill names are invisible in a terminal listing. I built six deliberately confusing names, compared what ls actually shows, and wrote a short check you can run before installing anything — plus an honest note on what that check misses.

Claude Code/2026-08-28Intermediate

Don't let your verification script's full output flow back through a hook

The check was working the whole time. The conversation was what ran out of room. Measured side by side: one scan of 833 files returns 58 bytes, another returns 42KB. Here is how to put an output budget on your hooks.