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 commands/varienos/agentic-workflow/g.skeletongit clone --depth 1 https://github.com/varienos/agentic-workflowWhat 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 | $0.00040 | $0.01770 |
| Opus 5 | $0.00020 | $0.00885 |
| Sonnet 5 | $0.00008 | $0.00354 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
g 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 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.
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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/g — Graphify Hızlı Komut
Graphify knowledge graph üzerinde hızlı sorgu çalıştırır. Bash("graphify ...") çağrısının kısa formu.
Argüman Parse
$ARGUMENTS ilk kelimesi mod belirler. Geri kalan kelimeler argüman olarak geçirilir.
| Mod | Komut | Açıklama |
|---|---|---|
query <soru> |
graphify query "<soru>" |
BFS traversal — kod ilişkisi keşfi (default 2K token) |
explain <Node> |
graphify explain "<Node>" |
Node + komşu özeti |
path <A> <B> |
graphify path "<A>" "<B>" |
İki node arası en kısa yol |
report |
head -100 graphify-out/GRAPH_REPORT.md |
God-node listesi + community map |
health |
(aşağıdaki health komutu) | Graph yaşı + node sayısı + son güncelleme |
| (boş/tanınmayan) | (rehberi göster) | — |
Argüman Quote Kuralı
Mode'dan sonraki argümanlar bir BÜTÜN olarak graphify'a geçirilir. Quote içine al.
/g query OrderService kullanımları→graphify query "OrderService kullanımları"/g explain BalanceService→graphify explain "BalanceService"/g path PricingService OrderModel→graphify path "PricingService" "OrderModel"/g query "PricingService 503 fail-closed"→ tırnaklar zaten varsa olduğu gibi geçir
health Komutu
/g health çağrıldığında şu Bash komutunu çalıştır:
if [ ! -f graphify-out/graph.json ]; then
echo "❌ Graph yok. Bootstrap:"
<!-- GENERATE: GRAPHIFY_UPDATE_COMMAND_ECHO
Aciklama: Bootstrap tarafindan manifest verileriyle doldurulur. Bu blok /g health else durumunda kullaniciya rehber gosterir — komut CALISTIRILMAZ, sadece echo ile yazdirilir. Monorepo modulu aktifse multi-layer echo satirlari, aktif degilse tek `echo " graphify update <codebasePath>"`.
Gerekli manifest alanlari: project.codebasePath, project.subprojects (monorepo varsa), modules.active
Ornek cikti (monorepo aktif):
echo " graphify update backend.aps/app && \\"
echo " graphify update kurye.aps/src && \\"
echo " graphify update musteri.aps/src && \\"
echo " python3 ../Agentbase/scripts/graphify-merge-layers.py"
Ornek cikti (tek-katman):
echo " graphify update ../Codebase"
-->
else
AGE_HOURS=$(python3 -c "import os,time; print(int((time.time()-os.path.getmtime('graphify-out/graph.json'))/3600))")
NODES=$(python3 -c "import json; print(len(json.load(open('graphify-out/graph.json'))['nodes']))")
EDGES=$(python3 -c "import json; print(len(json.load(open('graphify-out/graph.json'))['links']))")
STATUS="OK"
[ "$AGE_HOURS" -gt 24 ] && STATUS="STALE (>24sa)"
[ "$NODES" -lt 4000 ] && STATUS="EKSIK (<4000 node)"
echo "📊 Graph durumu: $STATUS"
echo " Yaş: ${AGE_HOURS} saat"
echo " Nodes: $NODES"
echo " Edges: $EDGES"
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 · 140 lines · 40 tokens per session scan A d2adb218c73c
g is a command published in the GitHub repository varienos/agentic-workflow (58 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 1,770 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 commands, from other repositories
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
memory
Search, store, and manage AI Team Memory — agent expertise, decisions, learnings, and code patterns. File-based by default, with an optional memory MCP overlay.
triage-issues
Launch the Issue Triage Agent (Haiku) to categorize and prioritize GitHub issues.
do-it-retrospective
开关本项目的本地行为反馈记录,或输出已记录问题的去敏复盘报告。参数为 on / off / status / report。.
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".
verify
Verify factual claims in content using deep research methodology - fact-checks key assertions and updates NCI scores.