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/jimmypaolini/codebase/codependix-navigatenpx skills add JimmyPaolini/codebase --skill codependix-navigategit clone --depth 1 https://github.com/JimmyPaolini/codebaseWhat 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 | $0.00114 | $0.01448 |
| Opus 5 | $0.00057 | $0.00724 |
| Sonnet 5 | $0.00023 | $0.00290 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
codependix-navigate 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading a codependix graph
Codependix's exports are standing reference artifacts, not pass/fail reports. A repository that runs it has already answered "what depends on this" and committed the answer — usually as a Mermaid diagram in a readme, sometimes as JSON. Reading that is faster and more complete than re-deriving it by grepping for imports, and it is the right first move when scoping a refactor.
Look for a ## 🕸️ Codependix section, or for the marker pair
<!-- codependix:start name="..." -->, in a project's readme. The workspace's
own graph is exported once at the repository root.
Confirm it is current first
A committed graph is only as fresh as the last --write. Before trusting
one to scope a change, run codependix --check — it reports exactly which
exports disagree with a freshly built graph and writes nothing. If the graph
you are about to read is among them, --write first. The codependix-export
skill covers both modes.
A graph that is stale in the direction that matters — an edge added since the last write — is the one way this reference misleads rather than merely lags.
Four graphs, four different questions
| Graph | Answers |
|---|---|
| Nx Neighborhood | What one project needs from the workspace, and who breaks if it changes |
| Workspace graph | The whole repository's project-level dependency structure at once |
| NestJS module graph | What a project's container actually wires together at runtime |
| File import graph | Which of a project's own files import which others |
Pick by the scope of the question. A cross-project rename is a Neighborhood question; moving a file within a project is an import-graph question; "why does this service get that provider" is a module-graph question.
Nx Neighborhood: blast radius
A Neighborhood is deliberately one hop in each direction — what the project depends on, and what depends on it. It is not a transitive closure.
dependentsis the blast radius of a breaking change to the project's public surface: every project listed will need to compile against the new shape. Their own dependents are one hop further out, in their neighborhoods — walk outward project by project when the change is genuinely breaking, rather than assuming the list is complete.dependenciesis what the project is allowed to reach for. A project that needs something absent from this list needs a new dependency declared, not just an import written.- An edge marked
implicitwas inferred by Nx from configuration rather than read out of code, so grepping for an import will not find it.
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 · 121 lines · 114 tokens per session scan A b052353d2dae
codependix-navigate is a skill published in the GitHub repository JimmyPaolini/codebase (0 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 1,448 once invoked, about $0.0006 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 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…