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-lintnpx skills add postindustria-tech/agentic-toolkit --skill neograph-dev-lintgit clone --depth 1 https://github.com/postindustria-tech/agentic-toolkitWrote 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/postindustria-tech/agentic-toolkit/neograph-dev-lint)<a href="https://agentmods.dev/skills/postindustria-tech/agentic-toolkit/neograph-dev-lint"><img src="https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/neograph-dev-lint.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.02651 |
| Opus 5 | $0.00037 | $0.01326 |
| Sonnet 5 | $0.00015 | $0.00530 |
| Haiku 4.5 | $0.00007 | $0.00265 |
Grade A, and why
neograph-dev-lint 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 4d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neograph Lint System
Provides the architecture of lint(), how to extend it with new checks, the
template placeholder validation system, and the CLI wiring checklist. The lint
is a read-only analysis pass that walks the construct graph and reports issues
without modifying anything.
Architecture
lint() lives in src/neograph/lint.py. It walks all nodes in a Construct
(recursing into sub-constructs) and runs checks. Currently three check categories:
1. DI Binding Checks (original)
Validates that FromInput/FromConfig parameters have matching keys in the
provided config dict. Existing since v0.1.
2. Inline Prompt Placeholder Checks
Validates that ${var} placeholders in inline prompts match predicted input
dict keys. Added in neograph-0h3x.
Inline prompts only see raw dict keys from node.inputs -- no flattened fields
from render_for_prompt return types, and no framework extras like node_id,
project_root, or human_feedback. The _KNOWN_EXTRAS set
({"node_id", "project_root", "human_feedback"}) is explicitly subtracted from
valid keys for inline prompts (see valid_keys = predicted_keys | (known_vars - _KNOWN_EXTRAS)
at lint.py:231). This is because inline ${var} substitution skips the full
rendering pipeline (_render_with_flattening never runs).
3. Template-Ref Placeholder Checks
When a template_resolver is provided, reads template text for template-ref
prompts, extracts {placeholder} names, and validates against input keys.
Added in neograph-vkiw.
Template-ref prompts see the full set of available keys: predicted input keys +
flattened field names from render_for_prompt return annotations + all known
vars (including framework extras like node_id/project_root/human_feedback).
This is because the prompt_compiler receives the RenderedInput.for_template_ref
dict which merges rendered inputs with flattened fields and framework extras.
The valid key set is predicted_keys | known_vars (lint.py:236) -- no
subtraction of _KNOWN_EXTRAS.
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.
- 4d ago First seen · 277 lines · 75 tokens per session scan A 53253926b6c0
neograph-dev-lint is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 2,651 once invoked, about $0.0004 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.
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.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…