ProjectAJ14ProjectAJ14/eklavya/skills/toolprune/SKILL.md

toolprune

Skill29 starsChanged 22 days agoMITView on GitHub

Show the tools this repository's sessions load and never use, and deny or restore them in this checkout's .claude/settings.local.json when asked.

1 other project uses a version of this.

Adopted by

Most recently taken up by

microsoft/TokenEconomizertheir own version, first seen Nov 1, 2026

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
microsoft/TokenEconomizer★ 5ksame name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- cli/CLAUDE.mdCLAUDE.md
- eval/CLAUDE.mdCLAUDE.md
- hooks/CLAUDE.mdCLAUDE.md
- mcp/CLAUDE.mdCLAUDE.md
- skills/CLAUDE.mdCLAUDE.md
- web/CLAUDE.mdCLAUDE.md
- eklavya-dashboardSkill
- eklavya-designSkill
- verify-docsSkill
- gateSkill
- learnSkill
- levelSkill
- memorySkill
- modeSkill
- packSkill
- progressSkill
- quizSkill
- setupSkill
- skipSkill
- tutorSkill

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 0 are distinctive, and 6 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Every tool a session loads costs context on every request, used or not.
line 9
Very specific:
Run eklavya toolprune list with Bash and show what it printed: each proposed tool with its evidence, and any tools Eklavya already denied.
line 14
Very specific:
If the developer passed apply (all of them) or named tools, run eklavya toolprune apply [tool...].
line 16
Very specific:
If they passed restore, run eklavya toolprune restore [tool...].
line 19
Very specific:
If they asked what it saves, run eklavya toolprune measure and repeat its two lines as written: it counts listing lines of deferred tools …
line 21
Very specific:
Never edit .claude/settings.local.json yourself, and never apply without being asked: the deny list is the developer's file.
line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

/eklavya:toolprune

Every tool a session loads costs context on every request, used or not. Eklavya keeps, per repository, how many prompts and sessions have passed since each loaded tool was last used, and proposes the ones that went unused. It writes nothing until the developer says so.

Run eklavya toolprune list with Bash and show what it printed: each proposed tool with its evidence, and any tools Eklavya already denied.
If the developer passed apply (all of them) or named tools, run eklavya toolprune apply [tool...]. Say that the change takes effect from the next session, and that eklavya toolprune restore undoes it.
If they passed restore, run eklavya toolprune restore [tool...]. Say that restored tools are not proposed again.
If they asked what it saves, run eklavya toolprune measure and repeat its two lines as written: it counts listing lines of deferred tools only, and says it does not measure full definitions.

Never edit .claude/settings.local.json yourself, and never apply without being asked: the deny list is the developer's file. eklavya toolprune apply refuses when economy.toolprune is off, when the file is not valid JSON, or when .claude leads out of the repository through a symlink; report its reason as written. Built-in tools Claude Code needs to work (Bash, Read, Edit, Write, the search and web tools, Agent, Skill, ToolSearch, AskUserQuestion) and every Eklavya tool are never proposed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free