Claude Code /advisor
Shares rank 7 of 10 coding agent features by recommenders
Lets a model like Sonnet hand hard steps to Opus in a clean sub-agent context. One critic notes it burns through token budgets.
Lets a model like Sonnet hand hard steps to Opus in a clean sub-agent context. One critic notes it burns through token budgets.
10 people gave an opinion
- recommend it
- 8
- criticize it
- 2
- approval share
- 80%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 8 people recommend itNeeds 10 or more, not met.
- 4 recommenders for every criticNeeds 2 to 1 or better, 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
Hands hard steps up to Opus
“then /advisor is what you want: a sub-agent with a much cleaner context is spawned”
Comment from 27 Jun 2026 in “Show HN: Smart model routing directly in Claude, Codex and Cursor” “Sonnet can handoff work it can't handle to Opus”
Comment from 7 May 2026 in “Higher usage limits for Claude and a compute deal with SpaceX” “it will reach up when it thinks it needs to”
Comment from 9 Oct 2026 in “Why are coding agents so dumb?” Helpful, works well in practice
“advisor has been really good experience for me especially with having only a Pro plan”
Comment from 12 Jun 2026 in “/architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds” “Advisor and "time-travelling rules" (TTSR) work great”
Comment from 2 Oct 2026 in “Pi 1.0” “Advisor-mode has been very helpful indeed”
Comment from 25 May 2026 in “DeepSeek reasonix, engineered for low token cost during long running sessions”
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 /advisorThis page | 8 | 2 | 80% | 4 | — | — |
What people said
All 11 comments that mention it, newest first. Each links to the original comment.
“it will reach up when it thinks it needs to”
“far superior to any single model for most tasks of any real complexity”
“Advisor and "time-travelling rules" (TTSR) work great”
“which misses most of the benefit; since you want different model families, with different pretrains and posttrains”
“Also burns through token budgets”
“then /advisor is what you want: a sub-agent with a much cleaner context is spawned”
“Claude kind of has this already in their Advisor feature”
“advisor has been really good experience for me especially with having only a Pro plan”
“Advisor-mode has been very helpful indeed”
“Sonnet can handoff work it can't handle to Opus”
“Our Adviser doesn't just "talk"; it outputs an AISP 5.1 document”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.