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/forge-statusnpx skills add ggombee/code-forge --skill forge-statusgit 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 | $0.00047 | $0.01630 |
| Opus 5 | $0.00023 | $0.00815 |
| Sonnet 5 | $0.00009 | $0.00326 |
| Haiku 4.5 | $0.00005 | $0.00163 |
Grade B, and why
forge-status scanned grade B with 1 finding 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 2d ago.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
tail -10 .claude/state/quality.jsonl 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge-status
code-forge의 현재 런타임 상태를 회고/진단용 단일 뷰로 보여줍니다.
외부 도구 연동용 JSON surface도 제공 — forge status --json.
[즉시 실행] 아래 절차대로 상태를 출력하세요.
사용법
/forge-status → 사람 읽는 리포트 (상세)
/forge-status --json → JSON 출력 (forge-glow, CI 연동용)
/forge-status --week → 최근 7일 quality 추이
/forge-status --reflect → REFLECT flag 상세
Step 1: CLI 호출
플러그인이 제공하는 단일 surface를 호출:
${CLAUDE_PLUGIN_ROOT}/bin/forge status
--json 인자 있으면:
${CLAUDE_PLUGIN_ROOT}/bin/forge status --json
→ JSON 그대로 출력하고 종료. 사람이 호출했어도 --json이면 파이프라인 용도로 가정.
Step 2: 상세 섹션 추가
--json이 아닌 경우, bin/forge status 출력 다음에 아래 섹션 보강:
2-1. 최근 quality 이벤트 (있으면)
tail -10 .claude/state/quality.jsonl 2>/dev/null
각 이벤트를 사람 읽는 포맷으로 변환:
[2026-04-14 10:00] eslint PASS
[2026-04-14 10:00] tsc FAIL 2 errors
[2026-04-14 10:00] test-trigger WARN TC 없음: src/hooks/useFoo.ts
2-2. REFLECT flag 상세 (활성 시)
[ -f .claude/state/reflect.flag ] && cat .claude/state/reflect.flag
→ timestamp, failed_blocks, failed_files 파싱하여 테이블화.
2-3. Notepad 미리보기 (있으면)
if [ -f .claude/state/notepad.md ]; then
echo "=== Notepad 미리보기 ==="
head -20 .claude/state/notepad.md
fi
2-4. 최근 decisions (있으면)
if [ -f .claude/state/decisions.md ]; then
echo "=== 최근 결정 3건 ==="
grep -A 3 "^## " .claude/state/decisions.md | tail -15
fi
2-5. 사용량 (usage.jsonl)
if [ -f "$HOME/.code-forge/usage.jsonl" ]; then
echo "=== 이번 주 사용 Top 3 ==="
# 7일 이내 에이전트/스킬 집계 — POSIX awk (gawk 3-인자 match 금지: macOS에서 무동작이었음)
# ISO ts는 문자열 비교가 곧 시간 비교
CUTOFF=$(date -u -v-7d +"%Y-%m-%dT%H:%M:%SZ" 2>/dev/null || date -u -d '7 days ago' +"%Y-%m-%dT%H:%M:%SZ")
awk -v c="$CUTOFF" -F'"' '{
ts=""; name=""
for (i = 1; i < NF; i++) {
if ($i == "ts") ts = $(i+2)
if ($i == "name") name = $(i+2)
}
if (ts >= c && name != "") print name
}' "$HOME/.code-forge/usage.jsonl" | sort | uniq -c | sort -rn | head -3
fi
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.
- 2d ago First seen · 183 lines · 47 tokens per session scan B 08186d40ea37
forge-status is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,630 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…