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 skills add arcasilesgroup/ai-engineering --skill ai-codegraphgit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-codegraph)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-codegraph"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-codegraph/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-codegraph"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-codegraph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00138 | $0.01166 |
| Opus 5.5 | $0.00055 | $0.00466 |
| Sonnet 5.5 | $0.00028 | $0.00233 |
| Haiku 4.5 | $0.00014 | $0.00117 |
Grade A, and why
ai-codegraph 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 22d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-codegraph — semantic code intelligence via MCP
What it produces
Nothing written. This skill reads the code graph and returns structured answers: verbatim source grouped by file, call paths (including dynamic dispatch), and blast radius summaries. The agent uses these to answer graph questions without grepping every file.
When to use CodeGraph vs find/grep
| Question | Tool | Why |
|---|---|---|
| "How does X work?" | codegraph_explore |
Follows call chains across files |
| "What calls function Y?" | codegraph_explore |
Graph traversal, follows polymorphism |
| "If I change this interface, what breaks?" | codegraph_explore |
Blast radius via edge traversal |
| "What does this module depend on?" | codegraph_explore |
Import edges in the graph |
| "Find all TODOs" | grep |
Literal text search, faster |
| "Where is X defined?" | find |
Simple path lookup |
| "Find all files importing X" | grep |
Literal text match |
| "Show me the test for this function" | find + grep |
Convention-based lookup |
Rule of thumb: graph questions → CodeGraph. Text questions → find/grep.
Steps
-
Check availability — is CodeGraph installed?
which codegraph && codegraph --versionIf missing:
npm i -g @colbymchenry/codegraph -
Check daemon — is the daemon running?
test -S .codegraph/daemon.sock && echo "running" || echo "not running"If not running:
codegraph serve --mcp & -
Check index — is the project indexed?
codegraph statusIf not indexed:
codegraph init -
Query — use
codegraph_exploreMCP tool:query: natural language or symbol/file namesmaxFiles: default 12, increase for broad questions
-
Interpret results — CodeGraph returns:
- Verbatim source grouped by file (with line numbers)
- Call paths (calls, imports, extends, implements)
- Blast radius summary (what depends on the queried symbol)
Per-surface MCP configuration
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.
- 22d ago First seen · 116 lines · 138 tokens per session scan A 2f30556b0b2e
ai-codegraph is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 138 tokens to every session and 1,166 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
spk-admin-setup-doctor
Install, verify, and repair Spec Kitty commands, skills, agent paths, runtime prerequisites, and common setup failures.
022-root-cause-analysis
Use when a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis point of view needs evaluation, or when a maintainer directly asks to find the…
126-java-exception-handling
Use when you need to apply Java exception handling best practices — including using specific exception types, managing resources with try-with-resources, securing exception messages, preserving error context via exception chaining, validating inputs early with fail-fast principles, handling thread interruption…
extracting-code-structure
Use when listing all methods, functions, or classes in a file, exploring unfamiliar code, getting API overviews, or deciding what to read selectively without loading entire files.
skill-performance
AL performance optimization patterns for Business Central. Use when optimizing queries with SetLoadFields, working with FlowFields and CalcFields, profiling codeunits, or resolving performance issues.
performance-optimization
Spring Boot 4 / JVM performance work — measure first, then fix. Profiling (async-profiler, JFR, JMH), Micrometer, common Spring antipatterns (N+1, unbounded lists, HikariCP sizing, virtual-thread pinning), caching, GC, and SLO-driven work. Used by /plan for risk callouts and by /review to flag perf regressions.