# drona23/claude-token-efficient

One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.

Repository: https://github.com/drona23/claude-token-efficient
Canonical: https://ross.abutalabs.com/products/claude-token-efficient
Language: Python
License: MIT
License Family: permissive
Last push: 2026-06-16T03:10:06+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 35, longevity 11
- inputs: {"age_days": 156, "days_push": 78, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5982, forks 463 (observed 2026-08-28T04:09:33.959110+00:00)

## What it is
A single drop-in CLAUDE.md configuration file that makes Claude Code responses terse and reduces output token usage on heavy workflows. It requires no code changes and works with any model that reads context instructions.

## Use cases
- reduce claude code output tokens
- make claude responses terse
- cut llm api costs on automation pipelines
- get consistent parseable output from claude
- stop claude from adding filler and unsolicited suggestions

## When to choose
- automation pipelines or agent loops with high output volume
- repeated structured tasks where verbosity compounds across many calls
- teams needing consistent output format across sessions

## When to avoid
- single short or casual one-off queries where the context overhead is a net token increase
- fixing deep failure modes like hallucinated implementations
- pipelines needing guaranteed parseable output - use structured outputs instead
- workflows spawning fresh sessions per task

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, llm-inference, developer-tools
- domain: large-language-models, developer-tools
- platform: cli, cross-platform
- tags: claude-code, claude-md, token-optimization, prompting, config-file, automation

## Member repositories
- drona23/claude-token-efficient (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:33.959110+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:49:53.179397+00:00, confidence not recorded.
  - readme: https://github.com/drona23/claude-token-efficient (fetched 2026-08-28T04:09:33.959110+00:00, sha bbf99b2724e0)
- Data as of 2026-08-30T08:39:29.467469+00:00.