token-saver

token-saver is a skill for Claude Code, Codex from roedyrustam/vibes-plug. It costs 45 tokens per session (1,224 once invoked), scanned A, original, MIT.

A communication skill for keeping long AI coding sessions brief and focused on essential changes.

In plain words
What is it for?
It helps produce concise replies, small diffs, and efficient multi-file reading during extended coding work.
Why use it?
It reduces unnecessary explanation and repeated context, helping conserve the conversation's token budget.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps produce concise replies, small diffs, and efficient multi-file reading during extended coding work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/roedyrustam/vibes-plug/token-saver
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.

Any agent
npx skills add roedyrustam/vibes-plug --skill token-saver
Clone the repo
git clone --depth 1 https://github.com/roedyrustam/vibes-plug

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for token-saver

README.md
[![agentmods](https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/token-saver.svg)](https://agentmods.dev/skills/roedyrustam/vibes-plug/token-saver)
Your own site
<a href="https://agentmods.dev/skills/roedyrustam/vibes-plug/token-saver"><img src="https://agentmods.dev/badge/skills/roedyrustam/vibes-plug/token-saver.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,224 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 38
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 5.1 $0.00045 $0.01224
Opus 5 $0.00023 $0.00612
Sonnet 5 $0.00009 $0.00245
Haiku 4.5 $0.00005 $0.00122

Measured 4d ago against content hash 84f048f52e8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

token-saver 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 4d 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.

skills/token-saver/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Token Saver Protocol (2026 Edition)

English | Bahasa Indonesia


English

Description

Implements token-efficient communication protocols for long-context AI coding sessions. Activates concise mode — minimizing response verbosity while maintaining precision and completeness of technical output.

Trigger Conditions

  • User asks for token-saving mode, concise responses, or minimal output.
  • Session is running long and context window is being consumed rapidly.
  • User explicitly says "be concise", "save tokens", or "minimal".

Token Budget Strategies for Long Context

1. Response Compression Rules (Active When Triggered)
  • No preamble: Skip "Of course! I'll help you with that...".
  • No restatement: Never repeat back what the user just said.
  • No trailing summaries: Don't summarize what you just did at the end.
  • Code-first: Show the code change immediately, explain briefly after.
  • Diff format: For small changes, show only the changed lines (not the full file).
  • Bullet > prose: Use bullet lists instead of paragraphs for explanations.
2. Tool Call Efficiency
  • Batch parallel reads: Read multiple files in a single turn (not sequentially).
  • Targeted grep over full reads: Use grep_search to find specific content before reading the whole file.
  • Write once: Produce correct output on first try — avoid edit-then-edit-again cycles.
  • Skip confirmation requests: Don't ask "Shall I proceed?" — just proceed.
3. Context Window Budget Awareness

When working on a long session:

Token budget allocation (for 200K context):
├── System prompt + skills:    ~15K
├── Conversation history:      ~50K (truncates older turns)
├── File contents read:        ~100K (most expensive)
└── Response generation:       ~35K
  • Prefer grep_search over reading full large files.
  • Summarize large files mentally; only view_file the specific section needed.
  • When context is nearly full, create a checkpoint with session-handoff-resume skill.

Read the full file on GitHub · 120 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. 4d ago First seen · 120 lines · 45 tokens per session scan A 84f048f52e8f

Subscribe to this mod's changes

token-saver is a skill published in the GitHub repository roedyrustam/vibes-plug (49 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,224 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

mm-setup

A setup guide that personalizes a shared mm system for one user. It asks for details such as your name, work area, tools, language, and Obsidian vault location, then saves them in private configuration files.

mworldorg/markdown-memory · 152 tokens

context-engineering

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

addyosmani/agent-skills · 43 tokens

self-improve

Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…

tobihagemann/turbo · 125 tokens

session-management

Context preservation, tiered summarization, resumability.

alinaqi/maggy · 13 tokens

recall-reasoning

Recall the reasoning behind a past change by locating the Claude Code transcript that produced it. Use when the user asks to "recall reasoning", "find reasoning", "look up reasoning", "recall implementation reasoning", "find the rationale", "why did I do X", "recall from transcripts", or "find the transcript for this…

tobihagemann/turbo · 76 tokens

update-turbo

Update installed Turbo skills from the local repo with a dynamic changelog, conflict resolution for customized skills, and guided user experience. Use when the user asks to "update turbo", "update turbo skills", "reinstall turbo", or "upgrade turbo".

tobihagemann/turbo · 54 tokens