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 skills add MadGraphTeam/MadAgents --skill ma-wiki-lintgit clone --depth 1 https://github.com/MadGraphTeam/MadAgentsWrote 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/madgraphteam/madagents/ma-wiki-lint)<a href="https://agentmods.dev/skills/madgraphteam/madagents/ma-wiki-lint"><img src="https://agentmods.dev/badge/skills/madgraphteam/madagents/ma-wiki-lint/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/madgraphteam/madagents/ma-wiki-lint"><img src="https://agentmods.dev/badge/skills/madgraphteam/madagents/ma-wiki-lint.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00093 | $0.01487 |
| Opus 5.5 | $0.00037 | $0.00595 |
| Sonnet 5.5 | $0.00019 | $0.00297 |
| Haiku 4.5 | $0.00009 | $0.00149 |
Grade A, and why
ma-wiki-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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ma-wiki-lint [targets]
A periodic tidy of the learned tier — the wiki at .madagents/wiki/ and each owner's MEMORY.md. It keeps what is already recorded well-formed, deduplicated, and balanced across the two tiers (MEMORY.md slate and wiki bodies). It reorganizes existing, already-cited content — it never source-walks, runs MadGraph, or authors a new principle.
Learning new content is a different job and lives elsewhere: ma-wiki-write records a finding on insight; generalization (lifting a deeper principle that catches more cases) fires on insight during mg-study / ma-reflect / mid-work via ma-wiki-write's generalize, never here; correctness of cached content is held by grounding-at-write, ma-reflect on a surfaced mistake, and /mg-deep-verify at point-of-use.
User-invoked only. Do not auto-invoke at session start or end.
Target
If the user did not name targets, ask: lead, named consultants, or all. Skip if .madagents/wiki/ is empty. Each owner tidies its own subtree — the memory-carrying agents (consultants and the probe) dispatched in parallel, the lead concurrent on lead/; no owner reads another's subtree.
Per-owner dispatch (tidy-mode)
"Tidy-mode dispatch on
.madagents/wiki/consultants/<your-agent-name>/(literal subtree path, suffix and all). Reorganize what is already recorded — do not source-walk, do not run MadGraph, do not author a new principle. Cheap fixes you apply viama-wiki-write; findings beyond your reach you list.Structural: (a) every page has parseable
description:frontmatter and only that field — flag/fix other keys; (b) descriptions ≥40 chars and not a trivial restatement of the filename; (c) no two pages share the same description (semantic duplicate → merge, below); (d) filenames not in blocklist (notes.md,misc.md,general.md,temp.md,todo.md,wip.md, dated filenames); (e) directory name exactly matches your agent's filename, suffix and all (e.g.ma-…-consultant, orma-probe); (f) MEMORY.md exists and is within budget (≤80 lines target, ≤120 hard cap; if over, demote stale entries); (g) MEMORY.md's wiki page index matches the actual pages in your subtree (fix missing/stale entries).Consolidate (reorganize existing content only — no new claims): (h) Merge two pages with the same trigger + behaviour, differing only in examples → one page; (i) Split a page whose body cleanly separates into two scopes that shouldn't co-load on one query; (j) Tier-balance — promote a wiki page's distillation into MEMORY.md when its principle is operative on most recent dispatches; demote a MEMORY.md entry that is internalized or long-unused.
Cross-subtree refs are not yours to update — flag them. Return: clean / N findings; one line per finding with the
ma-wiki-*operation applied; cross-subtree refs flagged."
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.
- 1mo ago First seen · 87 lines · 93 tokens per session scan A 3f4b95606d0c
ma-wiki-lint is a skill published in the GitHub repository MadGraphTeam/MadAgents (14 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 1,487 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…