agentleFS
toonighttoonight/get-shit-done-for-antigravity/.agents/skills/token-budget/SKILL.md

token-budget

Skill952 starsChanged 3 months agoMITView on GitHub

Manages token budget estimation and tracking to prevent context overflow

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Core principle: Every token counts. Load only what you need, when you need it.

    line 11
  2. Distinctive:

    Don't preload "just in case"

    line 105
  3. Distinctive:

    Always use context-fetch skill first:

    line 109
  4. Distinctive:

    Search for relevant terms

    line 110
  5. Distinctive:

    After understanding a file:

    line 116
  6. Distinctive:

    Document key insights in STATE.md

    line 117
  7. Distinctive:

    Use "I've analyzed X, it does Y" pattern

    line 119

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Token Budget Skill

<role> You are a token-efficient agent. Your job is to maximize output quality while minimizing token consumption.

Core principle: Every token counts. Load only what you need, when you need it. </role>


Token Estimation

Quick Estimates

Content TypeTokens/LineNotes
Code~4-6Depends on verbosity
Markdown~3-4Less dense than code
JSON/YAML~5-7Structured, repetitive
Comments~3-4Natural language

Rule of thumb: tokens ≈ lines × 4

File Size Categories

CategoryLinesEst. TokensAction
Small<50<200Load freely
Medium50-200200-800Consider outline first
Large200-500800-2000Use search + snippets
Huge500+2000+Never load fully

Budget Thresholds

Based on PROJECT_RULES.md context quality thresholds:

UsageQualityBudget Status
0-30%PEAK✅ Proceed freely
30-50%GOOD⚠️ Be selective
50-70%DEGRADING🔶 Compress & summarize
70%+POOR🛑 State dump required

Budget Tracking Protocol

Before Each Task

  1. Estimate current usage:
    • Count files in context
    • Estimate tokens per file
    • Calculate approximate %
  2. Check budget status:
    Current: ~X,000 tokens (~Y%)
    Budget: [PEAK|GOOD|DEGRADING|POOR]
  3. Adjust strategy:
    • PEAK: Proceed normally
    • GOOD: Prefer search-first
    • DEGRADING: Use outlines only
    • POOR: Trigger state dump

During Execution

Track cumulative context:

## Token Tracker

| Phase | Files Loaded | Est. Tokens | Cumulative |
|-------|--------------|-------------|------------|
| Start | 0 | 0 | 0 |
| Task 1 | 2 | ~400 | ~400 |
| Task 2 | 3 | ~600 | ~1000 |

Optimization Strategies

1. Progressive Loading

Level 1: Outline only (function signatures)
Level 2: + Key functions (based on task)
Level 3: + Related code (if needed)
Level 4: Full file (only if essential)

2. Just-In-Time Loading

  • Load file only when task requires it
  • Unload mentally after task complete
  • Don't preload "just in case"

3. Search Before Load

Always use context-fetch skill first:

  1. Search for relevant terms
  2. Identify candidate files
  3. Load only needed sections

4. Summarize & Compress

After understanding a file:

  • Document key insights in STATE.md
  • Reference summary instead of re-reading
  • Use "I've analyzed X, it does Y" pattern

Budget Alerts

At 50% Budget

⚠️ TOKEN BUDGET: 50%
Switching to efficiency mode:
- Outlines only for new files
- Summarizing instead of loading
- Recommending compression

At 70% Budget

🛑 TOKEN BUDGET: 70%
Quality degradation likely. Recommend:
1. Create state snapshot
2. Run /pause
3. Continue in fresh session

Integration

This skill integrates with:

  • context-fetch — Search before loading
  • context-health-monitor — Quality tracking
  • context-compressor — Compression strategies
  • /pause and /resume — Session handoff

Anti-Patterns

❌ Loading files "for context" — Search first ❌ Re-reading same file — Summarize once ❌ Full file when snippet suffices — Target load ❌ Ignoring budget warnings — Quality will degrade


Part of GSD v1.6 Token Optimization. See PROJECT_RULES.md for efficiency rules.

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.