Claude Skill

token-efficient-execution

Reduce token waste in long coding-agent sessions by avoiding repeated reads, noisy output, oversized context, broad rewrites, and unnecessary narration. Use on long tasks, heavy repos, multi-file audits, shell-heavy debugging loops, or whenever token budget is a practical deliver

LLM Mart · 0 points · 2 views 0 listing impressions 0 install-command copies
Download markoblogo-abvx-agent-skills-skills_token-efficient-execution-37a7146.zip · 3 KB

Install

skills CLI npx skills add https://github.com/markoblogo/abvx-agent-skills/tree/main/skills/token-efficient-execution
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install markoblogo-abvx-agent-skills@llmmart
Git git clone https://github.com/markoblogo/abvx-agent-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole markoblogo/abvx-agent-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Token Efficient Execution

Save tokens by tightening the work loop, not only the answer style.

Core Principle

The biggest waste usually comes from repeated exploration, repeated explanation, and oversized context reloads. Fix the loop first.

Execution Rules

  • Read targeted files, not whole trees.
  • Search exact symbols, error text, route names, or config keys before broad terms.
  • Do not reread the same file unless it changed or a new hypothesis makes it relevant.
  • Prefer narrow patches over file rewrites.
  • Avoid long “plan recap” messages after every small step.
  • Keep intermediary updates to one or two sentences unless the user asked for a plan.
  • Reuse gathered evidence instead of re-deriving it.
  • Stop low-value parallel exploration once a clear winning path appears.
  • Treat solution search as a stopping rule: once existing code, the standard library, a native feature, or the smallest viable patch satisfies the task, stop comparing already-excluded alternatives.
  • Do not widen adjacent tests, docs, or abstractions unless the changed behavior requires it. Preserve validation, security, accessibility, and data-safety work.

Task Patterns

Debugging

  • Build one reproducible signal.
  • Maintain a checked-location ledger.
  • Rank hypotheses before opening more files.

Implementation

  • Read surrounding code once, then patch.
  • Keep edits scoped to the behavior under change.
  • Run the narrowest verification first, then broaden only as needed.

Research

  • Keep an evidence ledger with claims, sources, and open questions.
  • Quote or cite only when needed.
  • Do not re-open sources already summarized unless precision requires it.
  • If the dominant waste is repeatedly loading the same long document, use doc-to-lora-evaluator before assuming a Doc-to-LoRA adapter is better than RAG, summaries, or direct context.

Anti-Patterns

  • broad grep loops over the same code;
  • rereading README, config, and the same module repeatedly;
  • restating the task after every command;
  • proposing before reading enough code;
  • validating everything when only one seam changed;
  • carrying stale notes forward after the code changed.

Final Report

Include what changed, what was verified, and any remaining uncertainty. Do not spend tokens listing every trivial command unless it matters for continuation.

Files (abvx-agent-skills)
  • agents
    • openai.yaml 218 B
      Loading…
  • SKILL.md 2.8 KB
    ---
    name: token-efficient-execution
    description: Reduce token waste in long coding-agent sessions by avoiding repeated reads, noisy output, oversized context, broad rewrites, and unnecessary narration. Use on long tasks, heavy repos, multi-file audits, shell-heavy debugging loops, or whenever token budget is a practical delivery constraint.
    license: MIT
    metadata:
      abvx_status: experimental
      abvx_origin: adapted
      abvx_eval_tier: rollout_checked
    ---
    
    # Token Efficient Execution
    
    Save tokens by tightening the work loop, not only the answer style.
    
    ## Core Principle
    
    The biggest waste usually comes from repeated exploration, repeated explanation, and oversized context reloads. Fix the loop first.
    
    ## Execution Rules
    
    - Read targeted files, not whole trees.
    - Search exact symbols, error text, route names, or config keys before broad terms.
    - Do not reread the same file unless it changed or a new hypothesis makes it relevant.
    - Prefer narrow patches over file rewrites.
    - Avoid long “plan recap” messages after every small step.
    - Keep intermediary updates to one or two sentences unless the user asked for a plan.
    - Reuse gathered evidence instead of re-deriving it.
    - Stop low-value parallel exploration once a clear winning path appears.
    - Treat solution search as a stopping rule: once existing code, the standard
      library, a native feature, or the smallest viable patch satisfies the task,
      stop comparing already-excluded alternatives.
    - Do not widen adjacent tests, docs, or abstractions unless the changed behavior
      requires it. Preserve validation, security, accessibility, and data-safety work.
    
    ## Task Patterns
    
    ### Debugging
    
    - Build one reproducible signal.
    - Maintain a checked-location ledger.
    - Rank hypotheses before opening more files.
    
    ### Implementation
    
    - Read surrounding code once, then patch.
    - Keep edits scoped to the behavior under change.
    - Run the narrowest verification first, then broaden only as needed.
    
    ### Research
    
    - Keep an evidence ledger with claims, sources, and open questions.
    - Quote or cite only when needed.
    - Do not re-open sources already summarized unless precision requires it.
    - If the dominant waste is repeatedly loading the same long document, use `doc-to-lora-evaluator` before assuming a Doc-to-LoRA adapter is better than RAG, summaries, or direct context.
    
    ## Anti-Patterns
    
    - broad `grep` loops over the same code;
    - rereading README, config, and the same module repeatedly;
    - restating the task after every command;
    - proposing before reading enough code;
    - validating everything when only one seam changed;
    - carrying stale notes forward after the code changed.
    
    ## Final Report
    
    Include what changed, what was verified, and any remaining uncertainty. Do not spend tokens listing every trivial command unless it matters for continuation.
    
  • SKILL_CARD.md 2.2 KB
    Loading…

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.