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/simplify-specnpx skills add WolframResearch/AgentTools --skill simplify-specgit 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 | $0.00084 | $0.00837 |
| Opus 5 | $0.00042 | $0.00418 |
| Sonnet 5 | $0.00017 | $0.00167 |
| Haiku 4.5 | $0.00008 | $0.00084 |
Grade A, and why
simplify-spec 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simplify a Design Specification
Rewrite a design specification to focus on user-facing behavior, removing or condensing internal implementation details. The goal is a spec that clearly communicates what the feature does and how users interact with it, without prescribing how it's built internally.
Spec to simplify: $ARGUMENTS
If no specific spec is given, ask the user which spec in Specs/ they'd like simplified.
Process
1. Read the Spec
Read the full spec file from Specs/. Identify every section and classify it:
- User-facing: Things a user of the paclet would see or interact with (function signatures, options, usage examples, option tables with types/defaults/descriptions, backward compatibility notes, future plans)
- Internal: Things only a developer implementing the feature would need (file modification lists, internal function signatures, internal symbol declarations, serialization details, parsing logic, private API code, environment variable plumbing, verification/test checklists)
2. Understand the Feature
Before rewriting, read the relevant source files to understand what the feature actually does. This is important because the spec may describe planned behavior that differs from what was implemented, or use terminology that's clearer in context.
Use the Explore agent or read files directly to understand:
- How users interact with the feature (the public API)
- What the actual defaults and option values are
- Which parts of the spec correspond to internal plumbing vs user-visible behavior
3. Rewrite the Spec
Apply these guidelines:
Remove entirely:
- File modification tables ("Files Modified")
- Internal symbol declarations (e.g., "Add to CommonSymbols.wl")
- Internal function implementations (e.g., full
toolOptionValuecode withEnclose/ConfirmBy) - Serialization/storage mechanism details (e.g., JSON format, environment variable names, parsing logic)
- Verification/test step checklists
- "Goals" sections that describe internal engineering goals rather than user value
- Strikethrough notes about removed plans (e.g., "
Deprecate the existing...(removed — ...)")
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 · 71 lines · 84 tokens per session scan A 8d85fe43ba62
simplify-spec is a skill published in the GitHub repository WolframResearch/AgentTools (82 stars, last pushed 6d ago), licensed MIT. It adds 84 tokens to every session and 837 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 2026-08-30.
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…