tokensaver
Skill1 starsChanged 45 days agoMITView on GitHub
Pick the right TokenSaver tool for the task. Use when the user asks to save context tokens, reduce token cost, read a web page, summarize logs, scan for secrets or prompt injection, query large JSON, aggregate MCP servers, or orient in an unfamiliar repository — this skill routes to the correct tool in the family.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Brucee/tokensavertheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Brucee/tokensaver★ 41same 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 repository9 other files it gives its agents.
- commitsmithSkill
- context-budgetSkill
- gatewaySkill
- injection-guardSkill
- json-lensSkill
- log-tailSkill
- repo-mapSkill
- secret-scanSkill
- web-snapshotSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
Every tool reports its token cost and honors budgets.
- Distinctive: line 36
Prefer the MCP tools; each skill also lists a CLI fallback for shells and hooks.
- Very specific: line 45
If a tool is missing, verify the server names in .mcp.json and that npx can resolve the package.
≈ “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.
Files
TokenSaver family
Nine tools that stop coding agents from burning context. Each has its own skill; this is the map.
Router
| Situation | Skill |
| Orient in a repo, find a symbol, outline a file | repo-map |
| Audit how many tokens MCP tools cost | context-budget |
| Read a web page as clean markdown | web-snapshot |
| Summarize or search logs and tracebacks | log-tail |
| Check staged changes for secrets | secret-scan |
| Write a conventional commit from the diff | commitsmith |
| Inspect or query large JSON/JSONL | json-lens |
| Many MCP servers behind one endpoint | gateway |
| Screen untrusted content for prompt injection | injection-guard |
Shared principles
- Everything runs locally. No API keys, no telemetry, no content leaves the machine.
- Every tool reports its token cost and honors budgets.
- Prefer the MCP tools; each skill also lists a CLI fallback for shells and hooks.
Install check
The plugin wires seven MCP servers from .mcp.json. Two tools are CLI-only inside this family:
commitsmithruns through the terminal (it reads the staged diff directly).gatewayneeds its own config file (npx -y mcp-gateway init) before serving.
If a tool is missing, verify the server names in .mcp.json and that npx can resolve the package.
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
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.