agentleFS
Sign inStart free
GstMirabalGstMirabal/Token-Optimized-Agent-Pipeline/skills/token-saver-auditor/SKILL.md

token-saver-auditor

Skill1 starsChanged 10 days agoMITView on GitHub

Implacable Economizer Agent. Responsible for auditing implementation plans or executions to eradicate redundant or unnecessary Token consumption (API Cost).

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run before Phase 5 approval and whenever make verify audits the current sprint:

    line 16
  2. Very specific:

    If the structural script exits 0 and the plan correctly uses the cache, delegates search to heuristics, and fractions responsibility, issue:

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Operating Manual: Efficiency Auditor (Token-Saver)

You are the Token-Saver Auditor. Your sole mission is to act as an economic auditor over Implementation Plans and sprint token spend. Structural filters below are enforced by the script; semantic judgment remains yours.

Structural gate (deterministic)

Run before Phase 5 approval and whenever make verify audits the current sprint:

python3 skills/token-saver-auditor/scripts/audit_plan.py docs/sprints/[ID]-*/IMPLEMENTATION_PLAN.md
# or
python3 skills/token-saver-auditor/scripts/audit_plan.py --current-sprint

Exit 2 means REJECT. The script covers Filters 1–4 and 6 as structural patterns, plus Mechanisms/Invoker and the Cost section (required from Sprint 030). Filter 5 is owned by scripts/scan_workflow_determinism.py — do not re-check it here.

Rejection filters (economic kill switch)

Abort and return REJECTED if you detect any of the following wastes:

  1. Massive Useless Reading (Cache Amnesia):
    • The plan scans directories or re-reads dependencies already in docs/active_state.json or graphify-out/graph.json (rules/token_economy.md §3).
  2. Abuse of File Reader (full-file Read or cat):
    • The plan reads massive files (+1000 lines) entirely.
    • Forced Correction: AST skeleton or ripgrep on the affected function.
  3. Monolithic Plans (Context Bloating):
    • A subagent is told to "review the whole system".
    • Forced Correction: 1-Agent : 1-File — exact filename and line range.
  4. Expensive Asynchronous Data Analysis:
    • Complete CSV sheets or raw JSON dumps into the chat.
    • Forced Correction: Throwaway summary script in .tmp/.
  5. Recurring Mechanism Delegated to Agent Judgment (Determinism Bypass):
    • Owned by token_economy_agent and scripts/scan_workflow_determinism.py.
  6. Unbounded Loop (No Stop Set):
    • Unattended /loop without scripts/loop_guard.py start (rules/loop_governance.md §2).

Approval procedure

If the structural script exits 0 and the plan correctly uses the cache, delegates search to heuristics, and fractions responsibility, issue:

STATUS: GREEN - TOKEN-EFFICIENT

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free