Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· Developer Tools
Lemnos Cost Guard
Real-time API cost tracking, context bloat detection, and budget enforcement for OpenClaw agents. Use when setting up cost guardrails, checking daily spend,...
skill openclawclawhub Free
Real-time API cost tracking, context bloat detection, and budget enforcement for OpenClaw agents. Use when setting up cost guardrails, checking daily spend,...
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, references/model_pricing.md, scripts/auto_cost_report.py, scripts/context_analyzer.py, scripts/cost_report.py, scripts/task_cost_report.py
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.1.0
Provenance
- Publisher
- getlemnos32
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Lemnos Cost Guard
Zero-config API cost tracking for OpenClaw agents. Reads your session files directly β no manual logging required. Built by Lemnos AI β the AI operations company. GitHub: getlemnos32/cost-guard
Scripts
ScriptPurposescripts/auto_cost_report.pyZero-config β reads OpenClaw session JSONL files directly. No setup.scripts/task_logger.pyLog cost by task type for granular attributionscripts/task_cost_report.pyBreakdown by task typescripts/cost_report.pyReport from manually logged entriesscripts/context_analyzer.pyScan workspace for context bloatscripts/track_cost.pyLog a single cost entry manually Model pricing and routing rules: references/model_pricing.md
Quickstart (30 seconds)
# Daily cost check β no setup required python3 skills/lemnos-cost-guard/scripts/auto_cost_report.py --budget 10.00 --format brief Output: π° COST (today 09:14 UTC): $3.42 / $10.00 (34%) β OK 47 calls | 1,243,800 in + 18,400 out + 892,100 cached
Morning Briefing β Cost Section
Run both reports before sending briefing: # Auto report (reads sessions directly) python3 skills/lemnos-cost-guard/scripts/auto_cost_report.py --budget 10.00 --format brief # Task-level breakdown python3 skills/lemnos-cost-guard/scripts/task_cost_report.py --format brief Include output verbatim. Flag anything over 80% of budget.
Log Per-Task Costs
python3 skills/lemnos-cost-guard/scripts/task_logger.py log "briefing" "Daily briefing 2026-03-16" --cost 2.14 --calls 38 Logs to: task-log.jsonl (readable by task_cost_report.py)
Context Bloat Check (weekly or when costs spike)
python3 skills/lemnos-cost-guard/scripts/context_analyzer.py --workspace /root/.openclaw/workspace
Budget Rules
ThresholdActionβ₯80% of daily budgetWarn user, flag in briefingβ₯100% of daily budgetHard stop all non-revenue tasks. Notify immediately.Single call >500K input tokensImmediate alert β context bloat riskI/O ratio >50:1 on any callContext bloat warning β recommend compaction Recommended budgets: Scrape days (Mon/Wed/Fri): $15/day Standard days: $10/day
Context Loading Rules
Load ONLY what the current task requires. Never load all files by default. TaskLoadMorning briefingSOUL.md, USER.md, MEMORY.md, HEARTBEAT.md, today's memoryEmail outreachMEMORY.md (relevant section), sent-log.mdResearch taskReference files for that vertical onlyHeartbeat (nothing to do)HEARTBEAT.md only
Model Routing
See references/model_pricing.md for full pricing table. Task TypeModelCostFormat, classify, status checkHaiku$0.80/M inputResearch, drafting, analysisSonnet$3.00/M inputComplex reasoningSonnet + thinking~$3.00/M inputOpusNever (unless explicitly requested)$15/M input
Auto Report: How It Works
auto_cost_report.py reads OpenClaw's native session JSONL files at: /root/.openclaw/agents/main/sessions/*.jsonl Each API call writes message.usage.cost.total to the session file automatically. This script aggregates by date, model, and session β no manual tracking needed. # Today's cost python3 auto_cost_report.py --budget 10.00 # Specific date python3 auto_cost_report.py --date 2026-03-15 --budget 10.00 # Last 7 days, full breakdown python3 auto_cost_report.py --days 7 --budget 70.00 --format full
Cost Log Format (manual entries)
{ "ts": "2026-03-16T14:00:00Z", "task": "email_send", "model": "claude-sonnet-4-6", "input_tokens": 45000, "output_tokens": 1200, "ratio": 37.5, "cost_usd": 0.153, "notes": "Day 7 breakup batch β 7 emails" }
β If This Saves You Money
Star it on ClawHub β it helps others find it. 192+ downloads. Built for production. Zero marketing. By Lemnos AI β we deploy AI employees that cut admin overhead by 85%. GitHub: getlemnos32/cost-guard
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
4 Scripts2 Docs
- SKILL.md
- references/model_pricing.md
- scripts/auto_cost_report.py
- scripts/context_analyzer.py
- scripts/cost_report.py
- scripts/task_cost_report.py