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/yugasun/aiops/code-graphnpx skills add yugasun/aiops --skill code-graphgit clone --depth 1 https://github.com/yugasun/aiopsWhat 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 | $0.00068 | $0.00555 |
| Opus 5 | $0.00034 | $0.00278 |
| Sonnet 5 | $0.00014 | $0.00111 |
| Haiku 4.5 | $0.00007 | $0.00056 |
Grade A, and why
code-graph 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.
What it actually says
Code Graph
Build, query, and incrementally update a persistent knowledge graph for the target project. Infrastructure — other skills consume it via query; Flow Conductor checks freshness on session start.
Two-tier extraction
| Tier | Tool | Role |
|---|---|---|
| Structural | graphify | AST nodes, edges, communities, confidence — deterministic |
| Semantic | Model | Purpose, depth, impact — contextual |
graphify parses; the model annotates. Never replace graphify structural data with grep guesses.
Prerequisites
prerequisites.md — install graphifyy via uv/pipx/pip. Non-blocking if user declines.
Storage
| Path | Source | Purpose |
|---|---|---|
graphify-out/graph.json |
graphify | Structural graph |
.scratch/graph/annotations.json |
Model | Semantic layer |
Do not copy graph.json into .scratch/. Schema: graph-schema.md.
Operations
Detailed steps: build-steps.md.
/code-graph build— full scan + semantic annotation/code-graph query <subcommand>— read-only; patterns in query-patterns.md/code-graph update— incremental via graphify cache
Constraints
- graphify is the structural backbone — no grep-based dependency guessing
- Model adds semantic layer only; never override graphify edges
- Prefer
updateoverbuildwhen graph exists - Non-blocking on graphify failure — warn and continue
- Confidence-aware: EXTRACTED (1.0) vs INFERRED (0.5) vs AMBIGUOUS (0.2)
Flow Conductor
aiops-graph.js hook suggests /code-graph build when stale. Architecture health runs graph_build phase first (phases.py) — build when missing/stale, skip when fresh, user may decline (organic fallback in /improve-codebase-architecture).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 56 lines · 68 tokens per session scan A 9b4c070265a5
code-graph is a skill published in the GitHub repository yugasun/aiops (4 stars, last pushed 12d ago), licensed Apache-2.0. It adds 68 tokens to every session and 555 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
hashiiiii-images
Use this skill to create project images, especially flat geometric images with a dark background and one accent color.
hashiiiii-pull-request
Use this skill to create or edit a GitHub pull request with the repository template or the default structure.
hashiiiii-git
Use this skill to name a Git branch or write a commit message.
hashiiiii-issues
Use this skill to create or edit GitHub issues with a consistent body structure.
hashiiiii-locale
Use this skill to set or change locale preferences for a user, project, or local Git worktree.
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.