TokenMasterX for GitHub Copilot. Half the tokens, same answers. Up to 58% fewer tokens and up to 54% lower cold-start cost, with no drop in pass rate.

GitHub Copilot on about half the tokens, with the same pass rate.
It drops tool definitions a task never calls, finds and reads code through a symbol graph instead of grep dumps and whole-file reads, and trims tool output without breaking the provider's prompt cache.

Quickstart · How it works · Benchmarks

_{Measured in a pre-registered study on GitHub Copilot CLI, in bring-your-own-model mode, with GPT-6 Astra and Claude Opus 5.5. Costs come from GitHub's own per-call billing.}

Quickstart

1. Install the GitHub Copilot CLI plugin

copilot plugin marketplace add All-The-Vibes/TokenMasterX
copilot plugin install token-master@token-master

# Or load from a local checkout
copilot --plugin-dir ./token-master-plugin

2. Prepare the runtime (once)

TokenMaster's MCP server and hook run on their own Python 3.12 environment with exact pinned packages; setup rejects an interpreter whose packages differ from the pins. Setup also needs graphify on PATH and OpenAI's cl100k_base vocabulary in tiktoken's cache. If you set COPILOT_HOME, use it in place of $HOME\.copilot.

$plugin = "$HOME\.copilot\installed-plugins\token-master\token-master"  # or ./token-master-plugin in a checkout
$runtime = "$HOME\.copilot\token-master-runtime"
uv venv --python 3.12 $runtime
& "$runtime\Scripts\python.exe" -m ensurepip
& "$runtime\Scripts\python.exe" -m pip install -r "$plugin\requirements-runtime.txt"
& "$runtime\Scripts\python.exe" -c "import tiktoken; tiktoken.get_encoding('cl100k_base')"
uv tool install graphifyy  # the PyPI package that provides the graphify command

The tiktoken line downloads the 1.7 MB vocabulary once. Setup verifies its SHA-256 and never downloads anything itself. Offline, copy a verified cl100k_base.tiktoken to the machine and set BRAINSPACE_TOKENIZER_FILE to its path before you start Copilot, or pass it to brainspace_setup.py with --tokenizer-file.

3. Run `/token-master` in your repository

Start copilot in the repository and type /token-master. It indexes the repository with Graphify, which takes a few minutes on a large repository the first time. Then it runs two installers with the runtime: setup.py wires up tokenmaster-nav, and brainspace_setup.py adds the view output-shaping hook, the launcher, and /tokenomics. Approve the commands when Copilot asks. Besides $HOME\.copilot, they write .token-master/ and graphify-out/ in the repository and add any missing .gitignore lines for them.

Type /tokenomics anytime to view your token usage, GitHub charges, and TokenMaster savings.

4. Start Copilot CLI with dynamic tool routing (recommended)

Once /token-master has configured your host (or after running brainspace_setup.py --host copilot manually), start copilot through the installed launcher so unused auxiliary tool schemas are pruned automatically. Use the runtime's Python: in BYOK mode the launcher's shaping needs its tiktoken.

& "$HOME\.copilot\token-master-runtime\Scripts\python.exe" "$HOME\.copilot\token-master\brainspace_copilot_bridge.py" -- copilot

Normal GitHub sign-in: Applies Dynamic Tool Routing (--excluded-tools), Graph Code Navigation (tokenmaster-nav), the one-shot view output hook, and /tokenomics.
BYOK mode (COPILOT_PROVIDER_BASE_URL set): Also activates the local prompt-cache bridge (stable_session_prefix + wire-level rg/glob shaping).
Keep all built-in tools: Pass --all-tools before -- (or set TOKENMASTER_KEEP_TOOLS=agents,sql).

Uninstall

Remove TokenMaster's Copilot configuration before you remove the plugin, because the uninstall scripts ship inside it:

In Copilot CLI, type /token-master uninstall. It runs setup.py --host copilot --uninstall and brainspace_setup.py --host copilot --uninstall, which remove only what TokenMaster added: tokenmaster-nav, its agent, the view hook, and /tokenomics.
Run copilot plugin uninstall token-master@token-master, then copilot plugin marketplace remove token-master. If you installed with the older direct command, run copilot plugin uninstall token-master instead.
Optional, with Copilot closed: delete $HOME\.copilot\token-master (launcher and launch log) and $HOME\.copilot\token-master-runtime. Also delete the *.token-master-backup-* and *.token-master-owned.json files that uninstall leaves next to mcp-config.json, settings.json and agents\token-master.agent.md; the backups are full copies of those files, including other servers' settings. In each indexed repository, delete .token-master and its .gitignore line, and graphify-out with its line unless you use Graphify on its own.

If you already uninstalled the plugin, install it again, run step 1, then uninstall it.

How It Works

Dynamic Tool Routing (brainspace_copilot_bridge.py) — Stock Copilot CLI sends JSON schemas for SQL scratchpads, session-store SQL, background job managers, subagents, agent workflows, skills, and CLI docs on every turn (~5,500 to ~11,500 tokens/call). TokenMaster inspects your prompt, flags (--agent, --resume), and installed skills/agents—keeping the capabilities your task needs and pruning the rest via --excluded-tools.
Graph Code Navigation (tokenmaster-nav) — Combines Graphify call edges with a local SQLite AST index into 3 compact tools (locate, read_symbol, impact), capped under 2,400 tokens. Answers "who calls X?" in one turn instead of dumping 100k+ tokens of rg. Covers Python and Rust today.
Cache-Safe Output Shaping (request_policy.py) — Folds rg/glob output losslessly and compacts oversized view reads once when appended. Never rewrites earlier messages, so the provider's prompt cache stays valid.
Cache-Stable BYOK Bridge (stable_session_prefix) — Moves the per-session Session folder: UUID out of the system prompt in BYOK mode so sessions in the same folder share the cached prompt on call 1.

The invariants behind these four are stated as theorems and checked by Lean 4 in proofs/, along with the gaps the proofs found.

`/tokenomics` — `ccusage` for Copilot CLI

Track your measured Copilot CLI tokens, GitHub billing (total_nano_aiu), and estimated TokenMaster savings locally from <COPILOT_HOME>/session-store.db:

# Run directly in any terminal (spends 0 model tokens)
python $HOME\.copilot\token-master\tokenomics.py
python $HOME\.copilot\token-master\tokenomics.py session --since 20261020

Or type /tokenomics inside an interactive Copilot CLI session.

┌──────────┬───────────────┬──────────────┬────────────┬──────────────┬────────────────┬───────────────┐
│ Session  │ Models        │ Total Tokens │ Cost (USD) │ TokenMaster  │ Saved Tokens ≈ │ Saved (USD) ≈ │
├──────────┼───────────────┼──────────────┼────────────┼──────────────┼────────────────┼───────────────┤
│ 579e5c15 │ • gpt-6-astra │       22,278 │      $0.15 │ -            │              - │             - │
│ 9b2700f4 │ • gpt-6-astra │       16,847 │      $0.09 │ lean+bridge  │         16,674 │         $0.01 │
│ 5690993e │ • gpt-6-astra │       16,844 │      $0.02 │ lean+bridge  │         16,674 │         $0.07 │
├──────────┼───────────────┼──────────────┼────────────┼──────────────┼────────────────┼───────────────┤
│ Total    │               │       55,969 │      $0.26 │ 2/3 sessions │         33,348 │         $0.08 │
└──────────┴───────────────┴──────────────┴────────────┴──────────────┴────────────────┴───────────────┘

Benchmark Summary (GitHub Copilot CLI)

All runs used the copilot.exe binary against api.githubcopilot.com, verified against GitHub's per-call copilot_usage bills. Cold Cost prices every session's first call as a cache miss; Back-to-Back Cost runs sessions consecutively in one folder.

Benchmark	CLI Version	Model	Raw Tokens (`Stock → TM`)	Cold Cost	Back-to-Back Cost	Passed (`Stock vs TM`)
This Repo (29 tasks, pre-registered)	`1.0.98`	`gpt-6-astra`	−49.5% (`2.45M → 1.24M`)	−41.5% (`$8.91 → $5.21`)	−50.2% (`$6.83 → $3.40`)	29/29 vs 29/29
This Repo (29 tasks, pre-registered)	`1.0.98`	`claude-opus-5.5`	−38.0% (`2.67M → 1.66M`)	−34.0% (`$4.23 → $2.79`)	−40.1% (`$2.72 → $1.63`)	29/29 vs 29/29
Django 5.2 (15 tasks, pre-registered)	`1.0.98`	`gpt-6-astra`	−58.5% (`708k → 294k`)	−53.5% (`$3.40 → $1.58`)	−70.7% (`$2.36 → $0.69`)	15/15 vs 15/15
Django 5.2 (15 tasks, pre-registered)	`1.0.98`	`claude-opus-5.5`	−53.7% (`990k → 458k`)	−46.0% (`$1.81 → $0.98`)	−61.2% (`$1.11 → $0.43`)	15/15 vs 15/15
Django 5.2 (45 tasks, exploratory)	`1.0.78-3`	`gpt-6-astra`	−53.4% (`2.42M → 1.13M`)	−49.5% (`$11.55 → $5.83`)	−79.9% (`$11.55 → $2.33`)	45/45 vs 44/45
Django 5.2 (45 tasks, exploratory)	`1.0.78-3`	`claude-opus-5.5`	−51.6% (`3.46M → 1.67M`)	−46.0% (`$6.14 → $3.31`)	−60.8% (`$3.31 → $1.30`)	45/45 vs 44/45

Experimental Status & Documentation

Experimental Disclaimer: TokenMaster is an experimental research toolkit, not an official GitHub product. Default GitHub routing applies Dynamic Tool Routing, Graph Navigation (tokenmaster-nav), and the view output hook; the prompt-cache bridge requires BYOK mode (COPILOT_PROVIDER_BASE_URL). In interactive TUI sessions started without -p, pass --all-tools or TOKENMASTER_KEEP_TOOLS if you need subagents, agent workflows or background PowerShell polling mid-session.

All full experimental reports, pre-registered protocols, negative results (v1–v5), and raw evidence live under token-master-plugin/docs/ and evidence/:

Copilot CLI Results (1.0.98 & 1.0.78-3) · Pre-Registered 1.0.98 Protocol (PRS-6)
Launcher & BYOK Bridge Guide · /tokenomics Dashboard & Estimator Validation
Replica Studies & Negative Results: PRS-4 · PRS-3 · PRS-2 · PRS-1 (why history rewriting fails)
15-Minute Demo Script · Interactive HTML Demo Deck