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/madgraphteam/madagents/edit-docsnpx skills add MadGraphTeam/MadAgents --skill edit-docsgit clone --depth 1 https://github.com/MadGraphTeam/MadAgentsWhat 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 | $0.00031 | $0.00975 |
| Opus 5 | $0.00015 | $0.00487 |
| Sonnet 5 | $0.00006 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
edit-docs 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edit MadGraph Documentation
Guided workflow for editing the MadGraph documentation with parallel review and revision.
Task
$ARGUMENTS
If no task was given, ask the user what they want to change.
Workspace Setup
If a draft already exists from a previous edit, skip setup — reuse it.
Otherwise, call the get_doc_draft MCP tool to create a writable copy:
get_doc_draft("/workspace/docs_draft")
Workflow
Round 1: Edit
Invoke the doc-editor agent with the task. It edits the draft files at /workspace/docs_draft.
After it finishes, generate a diff using the MCP tool (this correctly handles the overview file which lives outside /madgraph_docs/):
get_doc_diff("/workspace/docs_draft")
Save the diff output to /workspace/docs_changes.diff.
Round 1: Parallel Review
Invoke ALL THREE reviews simultaneously — do not run them sequentially:
-
doc-style-reviewer agent — review the changed files for style and formatting
-
doc-quality-reviewer agent — review the changed files for structure, placement, duplication
-
verifier agent — extract and verify factual claims from the changed content. Dispatch with:
Extract and verify all factual claims from the documentation changes.
- Diff of changes:
/workspace/docs_changes.diff - Updated docs:
/workspace/docs_draft/
Read the diff to understand what was changed, then read the relevant files for full context. Only extract claims from new or changed content — do not extract claims from unchanged parts of the documentation.
Doc-specific extraction rules:
- Extract both factual claims AND executable code blocks.
- Any fenced code block tagged as
mg5,madgraph,mg5_amc,bash, orpythonthat involves MadGraph commands must be extracted. For each, include the source file and section for context, what the code block accomplishes, and the full code block content.
Doc-specific verification rules:
- MG5 code blocks must be executed to confirm they run without errors.
- Default values must be verified by reading source code (e.g.,
banner.py, template card files) — not by trusting existing documentation. - Check that claims do not contradict each other within the document.
- Do NOT verify: general physics concepts, high-level descriptions, cross-references, formatting, or style choices.
- If you discover pre-existing errors in the existing documentation (under
/madgraph_docs/) while verifying, report them separately as incidental errors.
Write verdicts to
/workspace/verify/verdicts.json. - Diff of changes:
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 · 108 lines · 31 tokens per session scan A cb7360054773
edit-docs is a skill published in the GitHub repository MadGraphTeam/MadAgents (10 stars, last pushed 26d ago), licensed MIT. It adds 31 tokens to every session and 975 once invoked, about $0.0002 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…