ASAsmod4n·Mar 31, 2026
Someone measured how this reduced token efficiency, spoilers: efficiency is highest without any instructions.
https://github.com/drona23/claude-token-efficient/issues/1
In Universal Claude.md – cut Claude output tokensdrona23
claude-token-efficient
Python2026–2026
drona23 / claude-token-efficient
claude-token-efficient
One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.
4Distinct people
4Mentions
0Explicit recommenders
6.2KGitHub stars
What to know before exploring
What it is
One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:03:16 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by hour4 dated mentions
Observed mentions: 2026-03-31 01:23:34 UTC to 2026-03-31 05:19:21 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Mar 31, 01:00 | 2026-03-31 01:00:00 UTC | 2026-03-31 02:00:00 UTC | 2 | 1 | 1 |
| Mar 31, 02:00 | 2026-03-31 02:00:00 UTC | 2026-03-31 03:00:00 UTC | 1 | 0 | 1 |
| Mar 31, 03:00 | 2026-03-31 03:00:00 UTC | 2026-03-31 04:00:00 UTC | 0 | 0 | 0 |
| Mar 31, 04:00 | 2026-03-31 04:00:00 UTC | 2026-03-31 05:00:00 UTC | 0 | 0 | 0 |
| Mar 31, 05:00 | 2026-03-31 05:00:00 UTC | 2026-03-31 06:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
4 sourcesI get where the authors are coming from with these: https://github.com/drona23/claude-token-efficient/blob/main/...
But I'd rather use the "instruction budget" on the task at hand. Some, like the Code Output section, can fit a code review skill.
In Universal Claude.md – cut Claude output tokens by 63%It seems the benchmarks here are heavily biased towards single-shot explanatory tasks, not agentic loops where code is generated: https://github.com/drona23/claude-token-efficient/blob/main/...
And I think this raises a really important question. When you're deep into a project that's iterating on a live codebase, does Claude's default verbosity, where it's allowed to expound on why it's doing what it's doing when it's writing massive files, allow the session to remain more coherent and focused as context size grows? And in doing so, does it save overall tokens by making better, more grounded decisions?
The original link here has one rule that says: "No redundant context. Do not repeat information already established in the session." To me, I want more of that. That's goal-oriented quasi-reasoning tokens that I do want it to emit, visuali
Read the rest
ze, and use, that very possibly keep it from getting "lost in the sauce."
By all means, use this in environments where output tokens are expensive, and you're processing lots of data in parallel. But I'm not sure there's good data on this approach being effective for agentic coding.
Universal Claude.md – cut Claude output tokens
471 points · Open discussion