← Back to Skills Marketplace
155
Downloads
0
Stars
0
Active Installs
6
Versions
Install in OpenClaw
/install token-stats-reporter
Description
Generate and append accurate token/cost statistics in replies with a reproducible local algorithm (snapshot+incremental log aggregation + dedupe). Use when u...
Usage Guidance
This skill appears to do what it claims: it reads local conversation logs to compute token and cost stats and writes local state files. Before installing, verify (1) you are comfortable that the script will read your ~/.openclaw/agents/main/sessions logs (these contain user/assistant messages), (2) the hardcoded run path in SKILL.md matches your install location or update the invocation to the actual script path, (3) you are okay with the skill's fail-closed behavior (it can block sending messages if the script fails), and (4) you review the bundled script (it is local and contains no network calls). Consider testing in a non-production instance first and backing up session/state files.
Capability Analysis
Type: OpenClaw Skill
Name: token-stats-reporter
Version: 1.3.0
The skill is a utility designed to aggregate and report token usage and costs by parsing local session logs. The Python script (`scripts/token-show.py`) implements an incremental aggregation algorithm that reads JSONL files from the agent's session directory (`~/.openclaw/agents/main/sessions/`), calculates statistics, and maintains state in a local JSON file to avoid redundant processing. The instructions in `SKILL.md` provide a clear workflow for the agent to append these statistics to its responses, including a 'fail-closed' validation gate to ensure reporting accuracy. The code uses only standard libraries, lacks network access, and contains no evidence of data exfiltration or malicious intent.
Capability Assessment
Purpose & Capability
The skill's description (generate token/cost stats) matches its actions: it reads local session jsonl files and aggregates usage, and writes local state/counter files. Minor mismatch: SKILL.md tells the agent to run a hardcoded path (/home/admin/.openclaw/...), while the bundled script contains portable path-detection logic; this could cause the documented invocation to fail on systems where that exact path doesn't exist.
Instruction Scope
Instructions are narrow and specific: run the bundled Python script immediately before sending replies, append one exact token line, and fail-closed if the script fails. The script only reads local session logs (~/.openclaw/agents/main/sessions) and updates workspace/memory state. This is within scope for token reporting, but noteworthy because the skill will block sending messages if the script fails (operational impact) and it reads full conversation logs (sensitive data) — however it does not network-out or request extra credentials.
Install Mechanism
No install spec; skill is instruction-only with a bundled Python script. There are no network downloads or external package installs, and the script is present in the skill bundle. Low install risk.
Credentials
The skill requests no environment variables or credentials, which is appropriate. It does require read access to session log files (conversation transcripts) and write access to its own workspace/memory files — this access is necessary for its purpose but involves exposure of conversation contents, so consider privacy implications.
Persistence & Privilege
The skill does not request always:true and does not modify other skills. It writes state and counter files under its own workspace/memory directory (token-agg-state.json, token-counter.json), which is expected for aggregation state.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install token-stats-reporter - After installation, invoke the skill by name or use
/token-stats-reporter - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.3.0
Scheme-1 output labels: 本次总消耗/本次计费token/月累计总消耗; synced SKILL.md and reporter script
v1.2.0
**Changelog for token-stats-reporter v1.2.0**
- Added "v1.2.0 Send Gate," enforcing strict validation steps before sending replies with token lines.
- Now blocks sending if script fails or validation does not pass, disallowing handwritten token/cost stats.
- Provides a standard fallback text when automatic stats are unavailable.
- Updated documentation with the new validation workflow to ensure accuracy and consistency in token reporting.
v1.1.2
- Minor update only: documentation and metadata unchanged.
- No functional changes introduced in this version.
v1.1.1
- Maintenance release with no user-facing changes.
- Documentation and functionality remain the same.
v1.1.0
**Major update: New local aggregation algorithm and script path for precise, reproducible token/cost reporting.**
- Bundled script (`scripts/token-show.py`) added, with all usage stats determined from local message logs.
- Output format updated: now includes in/out tokens, cache reads, monthly statistics, costs, and model info.
- Deduplication, stateful incremental aggregation, and robust file handling now mandated for all reporters.
- Reliability and portability rules clarified for consistent deployment.
- Documentation details exact workflow, data sources, and requirements.
v1.0.0
Initial release: standardized token stats output workflow
Metadata
Frequently Asked Questions
What is Token Stats Reporter?
Generate and append accurate token/cost statistics in replies with a reproducible local algorithm (snapshot+incremental log aggregation + dedupe). Use when u... It is an AI Agent Skill for Claude Code / OpenClaw, with 155 downloads so far.
How do I install Token Stats Reporter?
Run "/install token-stats-reporter" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Token Stats Reporter free?
Yes, Token Stats Reporter is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Token Stats Reporter support?
Token Stats Reporter is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Token Stats Reporter?
It is built and maintained by sinoslug (@sinoslug); the current version is v1.3.0.
More Skills