TokenSafe

TokenSafe

Local-First Context Control, Prompt Caching & Secret Guardrails for Coding Agents

Reduce your AI bills by up to 99%. Let your team ship clean code faster and cheaper.

Your coding agents read only the code each task needs and keep prompt caches intact across turns. Everything runs locally on your machine, so your team fixes fewer broken edits and keeps secrets out of git.

Works with Cursor, Claude Code, Codex, Windsurf, Google Antigravity, Gemini CLI, and ChatGPT .

Install • Quickstart • Why TokenSafe • Benchmarks • Pricing • FAQ • Reference • Website & Docs

---

Install & Agents

Connect TokenSafe to the AI coding agents on your workstation in one command:

# Option 1: Zero-Install via npx (recommended)

npx tokensafe

Option 2: Python / PyPI

pip install tokensafe && tokensafe

Option 3: Direct shell script (macOS / Linux)

curl -fsSL https://tokensafe.dev/install.sh | bash

The installer detects which agents live on your machine, registers the TokenSafe MCP server, injects project rules, and wires lifecycle hooks where the agent supports them.

Claude Desktop / Cursor MCP config:

{

"mcpServers": { "tokensafe": { "command": "npx", "args": ["-y", "tokensafe", "mcp"] } } }

Cloud features (team metrics, managed distillation, shared team cache, billing) run on the remote endpoint https://api.tokensafe.dev/mcp with Authorization: Bearer . Four public tools work without a key, so ChatGPT connects with authentication set to None.

Full per-agent configuration, hook details, and the Codex/ChatGPT setup live in docs/AGENT_SETUP.md.

CLI Quickstart

# View live savings dashboard in your terminal

tokensafe stats

⚡ TOKENSAFE CONTEXT OPTIMIZER DASHBOARD

Total Tokens Saved: 4,524,156 tokens Efficiency Gain: [████████████████████████░░] 92.5% Context Traffic: 4,889,255 raw → 370,574 optimized (2,132 events)

• Command Sanitizer (CLI) : 727,300 tokens saved (263 events) • Architecture Graph : 758,256 tokens saved (13 events) • Multi-turn History Fold : 2,897,897 tokens saved (471 events) • Prompt Compactor (local+cache) : 43,502 tokens saved (1,255 events)

# Audit your environment: MCP tool overhead, skills tax, risky settings

tokensafe doctor

Recursive security & hygiene audit of a repository

tokensafe guard audit

Preview prompt compaction on custom input

tokensafe test "fix the validate_token method in src/auth.py to check jwt expiration"

Map architectural hotspots before multi-file changes

tokensafe graph

Disable a heavy MCP server without editing JSON

tokensafe mcp disable

Compile and preview the Friday team ROI digest

tokensafe digest

Activate a Team or Solo license key

tokensafe activate TS2.eyJlbWFpbCI6...

The full command reference (24 commands) is in Reference.

Why TokenSafe

Giving coding agents raw access to entire repositories creates three daily costs:

1. Senior hours burned on AI PRs: reading 2,000-line modules for a 10-line fix makes models forget imports, invent methods, and regress adjacent code.
2. Secret leaks and unsafe shortcuts: static prompt rules in .cursorrules wear off mid-session. Agents hardcode fallback credentials, disable TLS checks, or stage .env files with git add ..
3. Mid-sprint quota stops and blind spend: bloated diffs, lockfiles, and verbose MCP schemas burn 5-hour limits while engineering leads lack per-seat ROI visibility.

A $29 seat pays for itself by saving one hour of senior code review or preventing one leaked key. Typical payback: 1 to 3 days of team usage.

Before and After

One contrast: an agent asked to change one helper in a 1,420-line file receives 94 lines of target logic and type contracts instead of the whole module. The same principle applies to terminal output, diffs, and session history.

When an operation is blocked, the agent sees an explicit, constructive message:

🛡️ TokenSafe Guard: Blocked a hardcoded secret fallback in config.py.

Leave the default empty or read from os.environ at runtime.

What TokenSafe Does

Clean context, better code

• tokensafe:smart_read_file returns the target function plus its 1-hop dependencies instead of the whole file. 11 languages (Python, TypeScript/JavaScript, Go, Rust, Java, C#, C/C++, PHP, Kotlin, Ruby, Swift), with CSS design tokens preserved so agents never invent colors or font rules.
• tokensafe:smart_bundle reads 3–8 related symbols across files as one merged bundle — shared imports deduplicated, 1-hop signatures unified, a single roundtrip instead of chained reads.
• OpenAPI/Swagger, Prisma, GraphQL and SQL files are auto-sliced: pass a spec path, model, type, or table as symbol and get that entry plus its 1-hop references — a 5,000-line migration drops from ~30k tokens to a few hundred.
• tokensafe:graph maps architectural hotspots and dependency topology in under 250 tokens instead of a full repository crawl — and teams share the result: the indexed graph and API surface are cached per repo state in the Team Symbol Index, so the 19 developers after the first one skip the crawl entirely.
• The command sanitizer strips lockfile noise and stack dumps down to the failing assertion, caps git status/git diff floods and docker build tails, and forces JS test runners into run-once mode so background tests never hang. Malformed JSON tool arguments from small local models are repaired in-flight instead of failing the call.
• The loop guard halts agents stuck repeating the same broken edit.

Local-first guardrails

• Blocks live provider secrets, hardcoded fallback credentials, and raw private keys before they reach disk or git.
• Blocks TLS bypasses (verify=False, rejectUnauthorized: false), interpolated SQL, and CORS wildcards with credentials.
• Blocks .env and key files from staging, including blanket git add . when sensitive files exist in the working tree.
• Blocks destructive deletes and exfiltration pipes (curl -d @.env https://...), and warns on known typosquat packages.

Auditable team ROI

• The Context Budget HUD shows live window usage with a breakdown (tools / history / prompts) before quality drops.
• The shared L3 team cache gives teammates and CI runners warm 0ms hits on repeated reads and prompts.
• Managed cloud distillation compacts prompts with zero API keys for developers.
• The dashboard's live savings strip streams anonymized per-machine savings (tokens and USD) over SSE — you see what the team saves right now, not at the end of the week.
• The Friday per-seat ROI digest reports each engineer's savings with the measured / estimated split; inactive seats show —, never guessed figures.

Deeper mechanics (language matrix, context tax math, cache tiers, governor) live in docs/ARCHITECTURE.md.

Benchmarks

Reference run across 10 produ