token-save

A setting that switches agent skills between higher-cost and lower-cost language models. It can be turned on, turned off, or queried for its current routing.

In plain words
What is it for?
It helps toggle the setting, view which model tier each skill uses, and inspect the default routing for unlisted skills.
Why use it?
It lets users trade model cost for capability across different skills without changing each skill separately.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/joseph27/claude-code-token-save/skill
Any agent
npx skills add joseph27/claude-code-token-save --skill skill
Clone the repo
git clone --depth 1 https://github.com/joseph27/claude-code-token-save

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 602 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00061 $0.00602
Opus 5 $0.00030 $0.00301
Sonnet 5 $0.00012 $0.00120
Haiku 4.5 $0.00006 $0.00060

Measured 2d ago against content hash ddbe56f64bdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

token-save 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 2d 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.

skill/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Token-Save Mode

What to Do

  1. Read current state from ~/.claude/token-save-mode (if file doesn't exist, default is off)
  2. Read routing config from ~/.claude/token-save-routing.json
  3. Determine action based on argument:
    • /token-save on → set to on
    • /token-save off → set to off
    • /token-save (no arg) → toggle current state
    • /token-save status → show current state + routing summary, don't toggle
    • /token-save routing → show full routing table with all skills per tier
  4. Write new state to ~/.claude/token-save-mode (skip for status/routing)
  5. Report the change to the user

Output Format

After toggling, read ~/.claude/token-save-routing.json and display:

Token-Save Mode: [ON/OFF]

[If ON:]
Model routing active (from ~/.claude/token-save-routing.json):
  Opus (max quality)  → [list skills from opus tier]
  Sonnet (balanced)   → [list skills from sonnet tier]
  Haiku (cheapest)    → [list skills from haiku tier]
  Default for unlisted skills: [default_when_on value]

Enforcement: CLAUDE.md global rule applies to ALL Agent() calls.

[If OFF:]
All skills use Opus (default behavior). Maximum quality, maximum cost.

Routing Config Location

~/.claude/token-save-routing.json — this is the single source of truth for tier assignments.

Enforcement Layer

The enforcement lives in ~/.claude/CLAUDE.md under "Token-Save Mode (Agent Model Routing)". It instructs Claude to:

  1. Check ~/.claude/token-save-mode before every Agent call
  2. Look up the skill/task in the routing config
  3. Apply the tier's model, or default_when_on if unlisted

Skills do NOT need their own token-save logic — the global CLAUDE.md rule handles it.

Moving a Skill Between Tiers

If the user asks to change a skill's tier (e.g., "move brainstorming to opus"), edit ~/.claude/token-save-routing.json directly:

  1. Remove the skill from its current tier's array
  2. Add it to the target tier's array
  3. Confirm the change

Read the full file on GitHub · 60 lines

Changes

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.

  1. 2d ago First seen · 60 lines · 61 tokens per session scan A ddbe56f64bdf

Subscribe to this mod's changes

token-save is a skill published in the GitHub repository joseph27/claude-code-token-save (2 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 602 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens