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/postindustria-tech/agentic-toolkit/neograph-dev-codebase-navnpx skills add postindustria-tech/agentic-toolkit --skill neograph-dev-codebase-navgit clone --depth 1 https://github.com/postindustria-tech/agentic-toolkitWhat 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 | $0.00066 | $0.00858 |
| Opus 5 | $0.00033 | $0.00429 |
| Sonnet 5 | $0.00013 | $0.00172 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
neograph-dev-codebase-nav 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neograph Codebase Navigation
Provides the import map, layer discipline, and module ownership rules for the neograph declarative LLM graph compiler. Prevents the most common agent mistake: importing from the wrong internal module.
The Golden Rule
Never guess import paths. Always grep first:
grep -rn "def function_name" src/neograph/
grep -rn "class ClassName" src/neograph/
Public API Imports
All public symbols re-exported from neograph/__init__.py:
# Core
from neograph import Node, Construct, compile, run, configure_llm
from neograph import Each, Oracle, Operator, Loop, ModifierSet
from neograph import Tool, ToolInteraction, tool
from neograph import FromInput, FromConfig, ExcludeFromOutput
from neograph import LintIssue, lint, describe_type, describe_value
# Decorators
from neograph import node, merge_fn, construct_from_functions, construct_from_module
# Registration (also available from neograph directly)
from neograph.factory import register_scripted, register_tool_factory, register_condition
# Renderers
from neograph import Renderer, XmlRenderer, DelimitedRenderer, JsonRenderer
from neograph.renderers import render_input
# Errors
from neograph import CompileError, ConstructError, ConfigurationError, ExecutionError
Frequent Import Mistakes
| Wrong | Right | Why |
|---|---|---|
from neograph._sidecar import register_scripted |
from neograph.factory import register_scripted |
_sidecar has accessors, not registration |
from neograph.tool import register_tool_factory |
from neograph.factory import register_tool_factory |
Factory at factory.py:107 |
from neograph._llm import describe_value (deferred) |
Top-level in _llm.py now |
Was promoted, stale deferred imports may exist |
from neograph._construct_validation import X in decorators.py |
Import in _construct_builder.py instead |
Layer discipline: decorators -> builder -> validation |
Layer Discipline
User code
|
@node / ForwardConstruct / runtime Node|Modifier <- DX layer (decorators.py)
|
Construct(nodes=[...]) <- IR layer (construct.py, validation)
|
compile() <- Compiler (compiler.py, state.py)
|
factory._make_*_wrapper <- Runtime dispatch (factory.py, _dispatch.py)
|
LangGraph StateGraph
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 · 109 lines · 66 tokens per session scan A a02ebc208e69
neograph-dev-codebase-nav is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 858 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…