Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ggombee/code-forge/statsnpx skills add ggombee/code-forge --skill statsgit clone --depth 1 https://github.com/ggombee/code-forgeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00045 | $0.00967 |
| Opus 5 | $0.00023 | $0.00483 |
| Sonnet 5 | $0.00009 | $0.00193 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
stats scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/stats — Bellows 사용량 통계
usage.jsonl 로그를 분석하여 에이전트/스킬 사용 통계를 보여준다.
[즉시 실행] 아래 절차를 따라 통계를 출력하세요.
입력: $ARGUMENTS
옵션
| 옵션 | 설명 | 예시 |
|---|---|---|
| (없음) | 전체 통계 | /stats |
--week |
최근 7일 | /stats --week |
--month |
최근 30일 | /stats --month |
--project |
현재 프로젝트만 | /stats --project |
실행 절차
Step 1: 로그 파일 확인
LOG_FILE="$HOME/.code-forge/usage.jsonl"
파일이 없으면:
사용 기록이 없습니다. 에이전트나 스킬을 사용하면 자동으로 기록됩니다.
Step 2: 통계 파싱
Bash로 usage.jsonl을 파싱한다.
기간 필터링:
--week: 최근 7일의 타임스탬프만 필터--month: 최근 30일--project:"project":"현재디렉토리명"만 필터- (없음): 전체
파싱 방법:
jq가 있으면 jq 사용:
# 에이전트 Top 5
jq -r 'select(.type=="agent") | .name' "$LOG_FILE" | sort | uniq -c | sort -rn | head -5
# 스킬 Top 5
jq -r 'select(.type=="skill") | .name' "$LOG_FILE" | sort | uniq -c | sort -rn | head -5
jq 없으면 grep/awk 폴백:
# 에이전트 Top 5
grep '"type":"agent"' "$LOG_FILE" | grep -o '"name":"[^"]*"' | sed 's/"name":"//;s/"//' | sort | uniq -c | sort -rn | head -5
# 스킬 Top 5
grep '"type":"skill"' "$LOG_FILE" | grep -o '"name":"[^"]*"' | sed 's/"name":"//;s/"//' | sort | uniq -c | sort -rn | head -5
Step 3: 출력 형식
## code-forge 사용 통계
**기간:** {시작일} ~ {종료일} ({총 N일})
**총 호출:** {총 횟수}회
### 에이전트 Top 5
| # | 에이전트 | 호출 | 비율 |
|---|---------|------|------|
| 1 | {name} | {count} | {%} |
| 2 | {name} | {count} | {%} |
| 3 | {name} | {count} | {%} |
| 4 | {name} | {count} | {%} |
| 5 | {name} | {count} | {%} |
### 스킬 Top 5
| # | 스킬 | 호출 | 비율 |
|---|------|------|------|
| 1 | {name} | {count} | {%} |
| 2 | {name} | {count} | {%} |
| 3 | {name} | {count} | {%} |
| 4 | {name} | {count} | {%} |
| 5 | {name} | {count} | {%} |
### 프로젝트별
| 프로젝트 | 에이전트 | 스킬 | 합계 |
|---------|---------|------|------|
| {name} | {count} | {count} | {total} |
### 일별 추이 (최근 7일)
{날짜}: {"█" * count} {count}
데이터가 적으면 (10건 미만) 간략 형식으로:
## code-forge 사용 통계
총 {N}회 사용 ({에이전트 X회, 스킬 Y회})
가장 많이 사용: {name} ({count}회)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 115 lines · 45 tokens per session scan A da5e24a5cd4c
stats is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 967 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
TRC20 Token Toolkit
Universal TRC20 token operations — transfer, approve, query balances, and fetch metadata.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
unit-converter
Converts between common units of measurement including temperature, distance, and weight.
web-scraping
Web scraping and data extraction best practices.
data-analysis
Data analysis workflow: ingest, validate quality, explore, analyze, report. Use when the user provides or references datasets (CSV, JSON, SQL, spreadsheets) or asks for statistics, aggregation, correlation, or chart generation.
context-generate
Assemble a context package (code graph, requirements, constraints, blast radius) before a downstream generation task runs - human-approved, source-attributed. Do NOT use for simple lookups.