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/nicov7/codebase-visualizer/code-graphnpx skills add NicoV7/codebase-visualizer --skill code-graphgit clone --depth 1 https://github.com/NicoV7/codebase-visualizerWhat 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 | $0.00000 | $0.00717 |
| Opus 5 | $0.00000 | $0.00358 |
| Sonnet 5 | $0.00000 | $0.00143 |
| Haiku 4.5 | $0.00000 | $0.00072 |
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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-graph
Use the code-graph MCP tools (or the codegraph CLI) instead of grepping when the question is structural.
Steps
- Not indexed yet? Run
index_repo(CLI:codegraph index) once; re-run withincremental=trueafter changes. - "Who calls X / what does X call" →
trace_path(function_name, direction=in|out|both). - "Show the architecture / visualize the codebase" →
get_architecture, orcodegraph uifor the interactive 3D code city — click a component to expand its files in place, click a file for its functions;--base mainadds PR diff badges;--flatgives the 2D no-WebGL map. Share exact views via the hash:#inside=a,b&file=comp:path&trace=N&focus=symbolId. - "What changed in this PR and what does it touch" →
diff_overlay(base): per-symbol added/removed line numbers plus hunks; combine with inboundtrace_pathon changed symbols for blast radius. - Arbitrary structure questions →
query_graphwith Cypher (nodes: Function, Class, File, Module; edges: CALLS, IMPORTS, CONTAINS).
Descriptions and reasons
- Before explaining a component, check
describe_component(symbol_id); write missing ones withset_descriptionfollowingdescribe-style.mdin this directory. Uselist_undescribedto drive a describe-the-codebase loop. - When you add, change, or explain non-obvious code, log the why:
record_reason(symbol_id, why, kind=exists|changed). Read history withwhy_trace.
After you build anything (the comprehension contract)
The engineer must come out understanding what you built. For every new or changed symbol:
set_description(symbol_id, ...)perdescribe-style.md— what it does, in their words not yours.record_reason(symbol_id, why, kind="changed")— the non-obvious WHY that the code cannot say.- Tell them: run
codegraph review --base <ref>— a guided walkthrough of what you built, stop by stop, with a persistent understanding ledger and a comprehension heatmap on the city. - Alternatively run the tour conversationally:
build_walkthrough(base)→ present each stop's WHAT/WHY/code →mark_understood(symbol_id)only after they confirm. Checkget_comprehension()to see what they still have not reviewed — and say so.
What ships with it
1 file 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 · 43 lines · 0 tokens per session scan A 73b6cb92fd33
code-graph is a skill published in the GitHub repository NicoV7/codebase-visualizer (0 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 717 tokens. 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
quick-recap
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.