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 skills add roedyrustam/vibes-plug --skill token-savergit clone --depth 1 https://github.com/roedyrustam/vibes-plugWrote 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/roedyrustam/vibes-plug/token-saver)<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>- NVIDIA SkillSpector warn
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.
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 5.1 | $0.00045 | $0.01224 |
| Opus 5 | $0.00023 | $0.00612 |
| Sonnet 5 | $0.00009 | $0.00245 |
| Haiku 4.5 | $0.00005 | $0.00122 |
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.
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
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_searchto 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_searchover reading full large files. - Summarize large files mentally; only
view_filethe specific section needed. - When context is nearly full, create a checkpoint with
session-handoff-resumeskill.
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.
- 4d ago First seen · 120 lines · 45 tokens per session scan A 84f048f52e8f
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.
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.
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.
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…
session-management
Context preservation, tiered summarization, resumability.
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…
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".