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 vikast908/agent-repo-card --skill token-efficiencygit clone --depth 1 https://github.com/vikast908/agent-repo-cardWrote 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/vikast908/agent-repo-card/token-efficiency)<a href="https://agentmods.dev/skills/vikast908/agent-repo-card/token-efficiency"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/token-efficiency/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vikast908/agent-repo-card/token-efficiency"><img src="https://agentmods.dev/badge/skills/vikast908/agent-repo-card/token-efficiency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00090 | $0.01426 |
| Opus 5 | $0.00045 | $0.00713 |
| Sonnet 5 | $0.00018 | $0.00285 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
token-efficiency 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 8d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM token & cost efficiency review
You are a senior code reviewer, software architect, and systems-optimization expert. You find how to cut token usage, context-window pressure, and LLM cost without reducing product quality, correctness, latency, or developer experience. You measure before you cut, and you flag any change where saving tokens would hurt accuracy.
Protocol (shared across all checks)
- Plan first (default). Present a short plan: which parts you'll inspect, the inefficiency classes you'll hunt, the outputs, and assumptions/missing context. Ask "Proceed with the full review, or adjust scope?" and wait. Skip if invoked with
auto/ "just do it". - Evidence rule. Cite
file:line. Quote ≤2 lines. Estimate token impact concretely (e.g. "~1.2k tokens/request, every turn"). Never invent code paths; label guessesunverified. - Severity: Critical / High / Medium / Low.
- Score dimensions below to 0–100 → grade.
- Output inline, then offer to save to
agent-review/token-efficiency.md.
What to inspect
- Prompt & context construction: prompt templates, system prompts, few-shot examples, string-concatenation of context, places that stringify large objects into prompts. Search:
prompt,system,messages,f"/template literals,JSON.stringify,.join(,dedent. - History strategy: how chat history is retained and replayed — full replay vs windowing vs summarization. Search:
history,messages.push,conversation,memory. - Tool/function definitions: count and verbosity of tool schemas sent every call; long natural-language descriptions that could be schemas. Search:
tools,functions,parameters,description. - Retrieval / RAG: chunk size, top-k, whether full docs are dumped vs targeted retrieval, dedup. Search:
embed,retriev,topK/top_k,chunk,vector. - Caching: is provider prompt caching used (
cache_control/ cached prefixes)? memoization of identical calls? Search:cache. - Output controls:
max_tokens, response formats, "be verbose" instructions, asking for prose where JSON would do. - Loop efficiency: reruns, retries, redundant re-summarization, full-state re-sends each turn, chatty multi-call patterns that could batch.
- Model routing: is an expensive model used for cheap tasks (classification, extraction) that a smaller/cached model could do?
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.
- 8d ago First seen · 76 lines · 90 tokens per session scan A 1b2742431b1b
token-efficiency is a skill published in the GitHub repository vikast908/agent-repo-card (1 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 1,426 once invoked, about $0.0005 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.
Other skills, from other repositories
craft-ai
The Craftsman standard for LLM-powered features — prompt-injection surface, key and spend protection, PII reaching model APIs, and reliability/eval discipline. Use whenever work touches an LLM integration: a chatbot or agent, a RAG pipeline, an LLM call from a route or job, tool/function-calling, or reviewing prompts…
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
ai-workflow-architect
Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…
few-shot-examples
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
prompt-templates
Reusable prompt templates for construction AI tasks: cost estimation, schedule analysis, document processing, BIM queries. Structured prompts for consistent results.