Claude Code Ultracode
Ranked 5 of 10 coding agent features by recommenders
People recommend it for unattended, fast coding work and for finding bugs in large codebases. The most common caveat is that it burns through tokens and usage quotas quickly, and some find it unreliable where correctness matters.
People recommend it for unattended, fast coding work and for finding bugs in large codebases. The most common caveat is that it burns through tokens and usage quotas quickly, and some find it unreliable where correctness matters.
25 people gave an opinion
- recommend it
- 12
- criticize it
- 13
- approval share
- 48%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 12 people recommend itNeeds 10 or more, met.
- 0.9 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Finds bugs in large codebases
“Giant review on an entire six month old code base. It found 61 bugs, about ten were notable. Pretty impressed.”
Comment from 10 Jun 2026 in “Claude Fable 5” “found a bunch of bugs and issues for me”
Comment from 12 Jun 2026 in “Claude Fable is relentlessly proactive” Works unattended for long periods
“These patterns help me leave it unattended for longer periods of time and return to a reasonable assurance of correct code.”
Comment from 6 Jul 2026 in “GPT-5.6 Sol Ultra will be in Codex” “A low-stakes project where you can let ultracode runaway from you in the CLI is the most fun.”
Comment from 13 Aug 2026 in “ChatGPT Desktop (Codex Desktop) for Linux” Fast on coding tasks
“For coding Opus 4.8 with ultracode is near perfect and doesn't grind away as many tokens”
Comment from 7 Jul 2026 in “Ask HN: Fable Thread (July 12th Edition)” “with ultracode, it goes fast.”
Comment from 18 Aug 2026 in “GPT-5.6 Sol Pricing Cut by 50%” Boosts productivity on heavy workloads
“heavy token-burning workflows are good for my productivity”
Comment from 2 Jun 2026 in “Anthropic confidentially submits draft S-1 to the SEC” “I find ultracode extremely useful.”
Comment from 6 Jul 2026 in “GPT-5.6 Sol Ultra will be in Codex”
What people warn about
Each mark is one comment
Burns tokens and quota quickly
“the cookie monster of token consumption. I only found it useful for massive parallel grunt work.”
Comment from 10 Jun 2026 in “Claude Fable 5” “Ultracode destroys your limits and I have not found it to be worth it in the slightest”
Comment from 10 Jun 2026 in “Claude Fable 5” “it ate my 5h quota while only getting halfway through the problem”
Comment from 8 Jul 2026 in “"We're extending access to Claude Fable 5 on all paid plans through July 12."” - Comment from 26 Jun 2026 in “Previewing GPT‑5.6 Sol: a next-generation model”
Unreliable where correctness matters
“I tried to refactor parts of a large code base with Fable+ultracode and it just keeps accidentally merging distinct concepts”
Comment from 9 Jul 2026 in “AI changes the economics of software rewrites” “its only useful if the work you are doing doesn't have correctness as a high priority”
Comment from 6 Jul 2026 in “GPT-5.6 Sol Ultra will be in Codex” “ultracode make no mistakes (/s)”
Comment from 9 Jun 2026 in “Claude Fable 5” Hyped features with little new
“Anthropic loves to release these relatively obvious features with hyperbolic names”
Comment from 1 Jun 2026 in “Claude Code Ultracode” “it's nothing new or revolutionary”
Comment from 26 Jun 2026 in “Previewing GPT‑5.6 Sol: a next-generation model”
Other coding agent features people recommend
The four most recommended other coding agent features, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude Code plan mode | 41 | 22 | 65% | 11 | — | — |
| Claude Code auto mode | 20 | 29 | 41% | 6 | — | — |
| Claude Code Routines | 16 | 27 | 37% | 2 | — | — |
| Claude Code Dynamic Workflows | 13 | 10 | 57% | 4 | — | — |
| Claude Code UltracodeThis page | 12 | 13 | 48% | 4 | — | — |
What people said
24 of the 27 comments that mention it, newest first. Each links to the original comment.
“It created insanely complex milestones/lanes that moved super slow”
“Claude with ultracode for design and planning”
“with ultracode, it goes fast.”
“A low-stakes project where you can let ultracode runaway from you in the CLI is the most fun.”
“I noticed this kind of stuff happens more with ultracode for some reason.”
“I tried to refactor parts of a large code base with Fable+ultracode and it just keeps accidentally merging distinct concepts”
“it ate my 5h quota while only getting halfway through the problem”
“For coding Opus 4.8 with ultracode is near perfect and doesn't grind away as many tokens”
“its only useful if the work you are doing doesn't have correctness as a high priority”
“These patterns help me leave it unattended for longer periods of time and return to a reasonable assurance of correct code.”
“I find ultracode extremely useful.”
“Ultracode is pretty good.”
“it burns 3 million tokens in half an hour with a single prompt”
“it's nothing new or revolutionary”
“found a bunch of bugs and issues for me”
“the cookie monster of token consumption. I only found it useful for massive parallel grunt work.”
“Ultracode destroys your limits and I have not found it to be worth it in the slightest”
“Giant review on an entire six month old code base. It found 61 bugs, about ten were notable. Pretty impressed.”
“ultracode make no mistakes (/s)”
“always return something that I find just trivial and not a real issue”
“heavy token-burning workflows are good for my productivity”
“Anthropic loves to release these relatively obvious features with hyperbolic names”
“it's confusing that ultracode is not enabled on the desktop”
“The workflow/ultracode mode is absolutely unbelievable.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.