Sibyllinesoft Scribe
Ranked 2 of 3 prompt compressors by recommenders
Cuts coding agent token use sharply on SWE-bench-style tasks, often more than RAG or grep read. Caveat: in worst cases it reads the whole file.
Cuts coding agent token use sharply on SWE-bench-style tasks, often more than RAG or grep read. Caveat: in worst cases it reads the whole file.
8 people gave an opinion
- recommend it
- 7
- criticize it
- 1
- approval share
- 88%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not 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
- 7 people recommend itNeeds 10 or more, not met.
- 7 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 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
Large token reduction for coding agents
“it turns out that this can reduce context usage in SWE-bench style tasks by >90% over RAG and grep/read”
Comment from 12 Jan 2026 in “Which programming languages are most token-efficient?” “the performance difference is extreme; up to 98% token use reduction on SWE-bench tasks”
Comment from 12 Jan 2026 in “Which programming languages are most token-efficient?” “I have a tool that reduces agent token consumption by 30%”
Comment from 23 Jan 2026 in “Unrolling the Codex Agent Loop” - Comment from 11 Jan 2026 in “Ask HN: What Are You Working On? (January 2026)”
What people warn about
Each mark is one comment
Reads whole file in worst cases
“It seems worth it as it saves context space but in worst case scenarios it fails by reading the whole file”
Comment from 21 Mar 2026 in “OpenCode – The open source AI coding agent”
Other prompt compressors people recommend
The two most recommended other prompt compressors, 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 |
|---|---|---|---|---|---|---|
| RTK | 43 | 44 | 49% | 8 | 1 mo4 owners | — |
| Sibyllinesoft ScribeThis page | 7 | 1 | 88% | 5 | — | — |
| AgentReady | 5 | 1 | 83% | 3 | — | — |
What people said
All 11 comments that mention it, newest first. Each links to the original comment.
“it was only one that had consistently high quality across multilingual speech with multiple speakers”
“giving you full control and ownership”
“check out Scribe an alternative medium frontend that's why better”
“It seems worth it as it saves context space but in worst case scenarios it fails by reading the whole file”
“I have a tool that reduces agent token consumption by 30%”
“the performance difference is extreme; up to 98% token use reduction on SWE-bench tasks”
“I can barely get a grasp on what I'm looking at here, or how to use it practically.”
“it turns out that this can reduce context usage in SWE-bench style tasks by >90% over RAG and grep/read”
“reducing agent token usage by ~80% in real world tasks”
“you get email-client-compatible code that you can version control and customize”
“I was surprised by how good the results is”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.