Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/all-the-vibes/tokenmasterx/token-masternpx skills add All-The-Vibes/TokenMasterX --skill token-mastergit clone --depth 1 https://github.com/All-The-Vibes/TokenMasterXWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/all-the-vibes/tokenmasterx/token-master)<a href="https://agentmods.dev/skills/all-the-vibes/tokenmasterx/token-master"><img src="https://agentmods.dev/badge/skills/all-the-vibes/tokenmasterx/token-master.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00074 | $0.00864 |
| Opus 5 | $0.00037 | $0.00432 |
| Sonnet 5 | $0.00015 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
token-master scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/token-master
This skill turns on TokenMaster's token-efficient routing for the repository the user is working in. It is the on-switch: it builds the code graph and installs the routing engine.
What it does
- Builds a structural code graph of the repo with
graphify(no LLM, fast) — the default, cheapest backend. - Stores it at
.token-master/graph.jsonand adds.token-master/to the repo's.gitignore. - Best-effort installs a second
codegraphbackend (AST-resolved call edges) for precision escalation, and indexes the repo with it. This needsnode+npm; if they are missing the plugin still works graphify-only (the agent is written without the codegraph server). - Installs/refreshes the
token-masterrouting agent (user scope) and its graph MCP servers.
The two backends are not interchangeable: graphify is the cheap default; codegraph is a targeted escalation for precision-critical or sparse-call-graph cases (see "After setup"). If graphify's call graph is sparse for the repo (common in JavaScript/TypeScript), setup prints a warning — that is the signal codegraph will do the call-resolution work on that repo.
How to run it
The setup script lives in this skill's own directory. Locate it reliably, then run it:
- Run
/skills info token-masterand read the skill's directory path from the output. - Run the script, passing that directory and the repo root (normally the current working directory):
python "<skill-dir>/setup.py" "<repo-root>"
Then relay the script's summary output to the user verbatim.
- If the script reports that
graphify(oruv) is not installed, tell the user to install the missing tool —uv tool install graphify(see https://github.com/safishamsi/graphify) oruvitself (https://docs.astral.sh/uv/) — then run/token-masteragain. - The routing agent is loaded at CLI startup, so the user must restart their CLI before routing takes effect (unless it is already active). The setup script prints the exact host-specific restart command in its summary — relay that line as-is rather than guessing the host.
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agent.template.claude.md 5.3 KB
- agent.template.copilot.md 5.7 KB
- brainspace_benchmark.py 1.4 KB runs code
- brainspace_mcp.py 6.1 KB runs code
- brainspace_posttooluse.py 7.6 KB runs code
- brainspace_setup.py 11 KB runs code
- brainspace/__init__.py 1.5 KB runs code
- brainspace/benchmark.py 15 KB runs code
- brainspace/ccr.py 11 KB runs code
- brainspace/compressors/__init__.py 2.2 KB runs code
- brainspace/compressors/code_compressor.py 13 KB runs code
- brainspace/compressors/json_compressor.py 6.0 KB runs code
- brainspace/compressors/logs_compressor.py 6.0 KB runs code
- brainspace/compressors/prose_compressor.py 6.9 KB runs code
- brainspace/router.py 7.5 KB runs code
- brainspace/tests/test_code_compressor.py 23 KB runs code
- brainspace/tests/test_json_compressor.py 17 KB runs code
- brainspace/tests/test_logs_compressor.py 16 KB runs code
- brainspace/tests/test_prose_compressor.py 11 KB runs code
- brainspace/tests/test_router.py 5.1 KB runs code
- brainspace/tokens.py 2.1 KB runs code
- graphify_mcp.py 13 KB runs code
- setup.py 23 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 64 lines · 74 tokens per session scan A 55e2bc15a5ab
token-master is a skill published in the GitHub repository All-The-Vibes/TokenMasterX (3 stars, last pushed 28d ago), licensed MIT. It adds 74 tokens to every session and 864 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
graft
This repo is indexed by graft/. For ANY task here, whether understanding how something works, finding where code lives, tracing what calls a symbol or what a change breaks, or scoping an edit, get your context from graft before grepping or reading source files.
windows-compat
Audit and harden this Rust repo (code-graph-mcp) for Windows correctness: path-spelling drift between producers, the 32,767-char command-line cap, index-key mismatches, and path predicates that assume one ecosystem's layout. Use whenever touching code that builds, compares, prints, or stores a filesystem path; that…
cc10x-router
THE ONLY ENTRY POINT FOR CC10X. Activate this skill for build, debug, review, and plan requests. Use when the user asks to implement, fix, review, plan, test, refactor, or continue code work. Trigger keywords: build, implement, create, write, add, review, audit, debug, fix, error, bug, broken, plan, design, architect…
token-saver-config
Configure and diagnose token-saver compression settings. Use when the user asks about adjusting compression levels, checking processor status, debugging hook issues, or reviewing savings statistics.
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
diff-driven-docs
Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.