跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
搜索与研究

token-budget-gate

Estimates token cost before a multi-step task and outputs a 4-tier Green/Yellow/Orange/Red gate verdict. Records actual vs. estimated after completion when a mechanical usage source exists. Triggers on "token budget", "how much will this cost", "will this be expensive", "estimate tokens", before long multi-agent tasks.

chrono-meta · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add chrono-meta/forge-harness --skill token-budget-gate

技能说明


name: token-budget-gate description: Estimates token cost before a multi-step task and outputs a 4-tier Green/Yellow/Orange/Red gate verdict. Records actual vs. estimated after completion when a mechanical usage source exists. Triggers on "token budget", "how much will this cost", "will this be expensive", "estimate tokens", before long multi-agent tasks. user-invocable: true allowed-tools: ["Read", "Bash"] model: sonnet complexity_routing: base: sonnet high: opus escalate_when: - multi_project_scope - unknown_task_type

token-budget-gate — Pre-Task Token Cost Gate

Multi-step and multi-agent tasks can silently consume large token budgets. This skill estimates cost before execution, outputs a gate verdict, and calibrates estimates against actual usage after completion — preventing surprise overruns without blocking legitimate work.

FH context: FH default execution tier is standard (~15K tokens). This skill gates against accidental full (~30K) or max (~60K+) consumption on tasks that could be handled lighter.


Triggers

  • /token-budget-gate
  • "token budget", "token cost", "how expensive", "will this use a lot of tokens"
  • "estimate tokens", "token estimate before we start"
  • Before invoking: agent-composer, sim-conductor, steel-quench (max-tier skills)
  • Automatically proposed when task description contains: multi-agent, parallel dispatch, full suite, all files, entire codebase

Gate Thresholds (defaults — user-configurable)

SignalVerdictAction
Estimated < 10K tokens🟢 GREENProceed without comment
10K–30K tokens🟡 YELLOWProceed with notice — suggest lighter approach if one exists
30K–60K tokens🟠 ORANGEConfirm before proceeding — present scope reduction options
> 60K tokens🔴 REDBlock + require explicit approval — present mandatory reduction

Custom threshold: user can set TOKEN_BUDGET_MAX=N in conversation or .claude/settings.json.


Execution Steps

Step 1. Parse Task Description

Extract task dimensions:

DimensionLow (×1)Medium (×2)High (×4)
File scope1–3 files4–10 files11+ files / whole codebase
Agent count0 (inline)1–2 agents3+ agents / parallel
Step depth1–3 steps4–8 steps9+ steps
IterationNone1 round2+ rounds (wave/loop)
Output sizeShort answerMedium docFull report / deck

Step 2. Estimate Token Cost

Base estimates per task type:

Task TypeBase EstimateNotes
Single file edit2KRead + edit + verify
Code review (1 PR)5KDiff + analysis + comments
Skill creation (1 SKILL.md)8KDesign + write + CATALOG update
Agent dispatch (1 agent)10KContext card + agent overhead
Parallel dispatch (3 agents)25K3× agent + orchestration
sim-conductor full run30KAll 5 simulation axes
steel-quench 4-wave50KAll waves + prescriptions
Full harvest-loop cycle40K8-step pipeline + PRs

Apply dimension multipliers from Step 1 to the base estimate.

Calibration override (read leg): if .claude/token_calibration/log.tsv exists and holds ≥1 row for this task type, derive the base as median(actual_i / mult_i) over its rows — each row's mult column records the dimension-multiplier product that was in effect, so dividing recovers a dimension-neutral base. Never use raw actual as the base: actual already contains that run's multipliers, and re-applying this run's multipliers on top double-counts scope. The table above is the uncalibrated default; measured local data outranks it. State which source the estimate used (base: table (uncalibrated) or base: calibration log, n={rows}).

Final formula:

Estimated = base × file_multiplier × agent_multiplier × iteration_multiplier

Round to nearest 1K.


Step 3. Output Gate Verdict

## Token Budget Gate

Task: {one-line task description}
Estimated cost: ~{N}K tokens
Threshold: {user max or default}

Verdict: 🟡 YELLOW — within budget but consider lighter approach

Breakdown:
  Base (skill creation): 8K
  × 2 agents: ×2 = 16K
  × 1 iteration: ×1 = 16K
  Total: ~16K

Lighter alternative:
  → Inline (no agent dispatch): ~8K (-50%)
  → Single agent, not parallel: ~12K (-25%)

Proceed? (y to continue / n to adjust scope)

For 🟢 GREEN: output one line only — "Token estimate: ~{N}K — GREEN, proceeding."


Step 4. Proceed / Adjust

  • GREEN / YELLOW + user confirms: proceed, note start marker
  • ORANGE: present scope reduction table, wait for user selection
  • RED: present mandatory reduction — do not proceed until user explicitly approves

Scope reduction options table (ORANGE/RED):

OptionReductionTrade-off
Drop parallel → sequential-30%Slower, same quality
Reduce agent count (3→1)-50%Less parallelism
Narrow file scope-40%Shallower coverage
Use lighter skill variant-60%Fewer waves/probes
Split into 2 sessions-50%/sessionNo quality loss

Step 5. Post-Task Calibration (offered, not required)

After task completion, if user says "how much did that cost" or "calibrate":

Actual must come from a mechanical source — the user pasting /cost output, or budget.spent() in a Workflow context. A model cannot read its own token consumption by introspection; a reconstructed number written into the log poisons every future estimate that reads it (the read leg in Step 2). No mechanical source available → render Actual: UNMEASURED and write no row.

## Calibration

Estimated: ~16K tokens
Actual: ~{actual}K tokens   (source: /cost paste | budget.spent() | UNMEASURED)
Error: {+/-N}%   (omit when UNMEASURED)

Write calibration data (only when Actual is mechanically sourced):

mkdir -p .claude/token_calibration/
# mult = this run's dimension-multiplie
阅读完整来源 ↗