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 marchatton/agent-skills --skill modular-skills-architectgit clone --depth 1 https://github.com/marchatton/agent-skillsWrote 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/marchatton/agent-skills/modular-skills-architect)<a href="https://agentmods.dev/skills/marchatton/agent-skills/modular-skills-architect"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/modular-skills-architect/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/marchatton/agent-skills/modular-skills-architect"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/modular-skills-architect.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 | $0.00067 | $0.02682 |
| Opus 5 | $0.00034 | $0.01341 |
| Sonnet 5 | $0.00013 | $0.00536 |
| Haiku 4.5 | $0.00007 | $0.00268 |
Grade A, and why
modular-skills-architect 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 8d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modular Skills Architect
the modular-skills-architect must flow
Consistency across skills not required. Do not standardize structure unless asked.
Canonical repo only (important)
Use this skill only in the canonical templates repo where agent instructions live (GitHub: marchatton/templates; local path may differ).
If you are running this from another repo:
- stop and switch to the canonical repo first, or you will refactor the wrong source of truth
- update this line to the correct canonical repo link/name for your org
Provenance + control model (also important)
Not everything is truly "owned" by this repo. Treat each artefact (skill/command/hook/agent file/template) as one of:
- Forked (you hold master)
- canonical source is your fork; you can change it here
- refactors can be implemented directly (still keep changes small)
- Synced / drifted
- you have a local or downstream copy that differs from what "master" says
- treat as risky until reconciled
- refactor output must include a sync plan: real source of truth + how to converge
- External (called, not stored)
- e.g. invoked via
npx <thing>likenpx agent-skills - you do not edit it here; you can only:
- wrap it (command wrapper)
- document it (how/when)
- pin versions
- replace it with an owned implementation (only if justified)
This skill must surface provenance early, and every recommendation must state which bucket it touches and what that implies (direct change vs wrapper vs upstream work vs reconcile).
Use when
- inherited messy skills/commands/workflows/AGENTS/docs and nobody can explain fit
- combining sources and need to consolidate + rationalise, keep it simple
- skills overlap, routing surprises, outputs inconsistent, glue logic in wrong place
- need concrete refactor plan (split/consolidate/rename/delete), not theory
Avoid when
- only need one existing workflow (
wf-*) and nothing structurally broken - missing almost all inputs and cannot locate corpus (still proceed if partial, label assumptions)
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.
- 8d ago First seen · 293 lines · 67 tokens per session scan A 20287c8b8b82
modular-skills-architect is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 67 tokens to every session and 2,682 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…