القائمة
Generate a monthly or on-demand cost report across LLM providers, local LLMs, and agent engines. Flags overspend and suggests downgrades.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Verify a feature spec, plan, or PR against the non-negotiable principles in `.specify/memory/constitution.md`.
Extract session insights after a task completes and feed them into Morphic's self-evolution engine. Captures what worked, what didn't, and proposes prompt/routing tweaks.
Keep CLAUDE.md (thin router) and AGENTS.md (telegraph-style) in sync. Detects drift in command lists, paths, and routing tables between the two root instruction files.
Run live end-to-end verification across Morphic-Agent's 6 agent CLI engines. Produces a baseline comparison table with duration and cost per engine.
Inspect Morphic-Agent's fractal task graph for a given task_id. Reports bypass classifier decisions, Gate 2 skips, parallelism, and regression flags.
Preview a LAEE action plan — classify risk, check undo availability, inspect credential touchpoints — without executing anything.
| name | cost-report |
| description | Generate a monthly or on-demand cost report across LLM providers, local LLMs, and agent engines. Flags overspend and suggests downgrades. |
| when_to_use | When user asks about spending, at month boundary, or when budget circuit breaker approaches 80%. |
| argument-hint | [period: today|week|month|YYYY-MM] |
| allowed-tools | ["Read","Grep","Glob","Bash(morphic cost report *)","Bash(sqlite3 * SELECT*)"] |
| model | sonnet |
You produce an actionable cost report.
$ARGUMENTS = period (default: current month).
cost-guardian subagent.infrastructure/persistence/*/cost_records.py (persisted aggregates).ollama_tokens / total_tokens × 100%.cached_tokens / input_tokens × 100%.month_to_date / monthly_cap × 100%.# Cost Report — <period>
## Summary
- Total: $X.XX
- Budget: $Y.YY (N% used)
- LOCAL rate: NN%
- Cache hit rate: NN%
## By provider
| Provider | Tokens in | Tokens out | Cost |
|---|---|---|---|
| anthropic | 1.2M | 340k | $4.20 |
| google | 800k | 210k | $0.15 |
| openai | 50k | 12k | $0.80 |
| ollama | 2.1M | 580k | $0.00 |
## By engine
(same format)
## Top 10 tasks by cost
1. task_7f3a... $1.20 (complex plan, Claude Sonnet)
2. ...
## Alerts
- ⚠️ 3 tasks exceeded $0.50 individual cap
- ⚠️ Cache hit rate dropped from 62% to 48% this week
## Suggested actions
- Raise LOCAL rate from 72% → 85% by routing all SIMPLE to ollama (est. -$X/mo)
- Enable prompt caching for /fractal-analyze (est. -$Y/mo)