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/wolframresearch/agenttools/add-code-inspector-rulenpx skills add WolframResearch/AgentTools --skill add-code-inspector-rulegit clone --depth 1 https://github.com/WolframResearch/AgentToolsWhat 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 | $0.02595 |
| Opus 5 | $0.00033 | $0.01298 |
| Sonnet 5 | $0.00013 | $0.00519 |
| Haiku 4.5 | $0.00007 | $0.00260 |
Grade A, and why
add-code-inspector-rule 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 2d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a Custom CodeInspector Rule
Follow this workflow to implement a new code inspection rule. The rule system lives in Kernel/Tools/CodeInspector/Rules.wl with tests in Tests/CodeInspectorTool.wlt.
Step 1: Understand the Rule
$ARGUMENTS
Clarify these details (ask the user if not clear):
- What code pattern should be detected? Get an example of the problematic code.
- Why is it problematic? This becomes the inspection message.
- Severity: Fatal (code will not run, parse etc.), Error (almost certainly a mistake), Warning (likely a mistake), Remark (suggestion), Formatting (style).
- Confidence: 0.95 for highly certain rules, 0.9 for confident, 0.7-0.9 for likely.
Step 2: Choose the Rule Type
| Type | When to Use | Add To |
|---|---|---|
| Abstract | Match simplified AST patterns (most common) | $customAbstractRules in Rules.wl |
| Concrete | Need whitespace/comments (e.g., comment content) | $concreteRules in Rules.wl |
| Aggregate | Analyze relationships between multiple AST nodes | $aggregateRules in Rules.wl |
| Text-level | Raw source text (line length, file size, etc.) | textLevelInspections function in Rules.wl |
Step 3: Explore the AST Structure
Use the WolframLanguageEvaluator tool to parse example code and understand its AST:
Needs["CodeParser`"];
(* For abstract rules: *)
CodeParser`CodeParse["problematic code here"]
(* For concrete rules: *)
CodeParser`CodeConcreteParse["problematic code here"]
Study the output to determine which node types and patterns to match. Key node types:
CodeParser`CallNode— function calls likef[x]CodeParser`LeafNode— atoms like42,"hello",SymbolCodeParser`InfixNode— infix ops likea + bCodeParser`PrefixNode— prefix ops like-x
Note: If you want to use symbols defined in Rules.wl in the WolframLanguageEvaluator tool during your exploration, you'll need to use their fully qualified names:
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.
- 2d ago First seen · 306 lines · 66 tokens per session scan A c1db2d611a48
add-code-inspector-rule is a skill published in the GitHub repository WolframResearch/AgentTools (82 stars, last pushed 7d ago), licensed MIT. It adds 66 tokens to every session and 2,595 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 2026-08-30.
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…