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 zhouyou-gu/skill-marketplace-template --skill hierarchical-agent-filesgit clone --depth 1 https://github.com/zhouyou-gu/skill-marketplace-templateWrote 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/zhouyou-gu/skill-marketplace-template/hierarchical-agent-files)<a href="https://agentmods.dev/skills/zhouyou-gu/skill-marketplace-template/hierarchical-agent-files"><img src="https://agentmods.dev/badge/skills/zhouyou-gu/skill-marketplace-template/hierarchical-agent-files/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/zhouyou-gu/skill-marketplace-template/hierarchical-agent-files"><img src="https://agentmods.dev/badge/skills/zhouyou-gu/skill-marketplace-template/hierarchical-agent-files.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 | $0.00086 | $0.02229 |
| Opus 5 | $0.00043 | $0.01115 |
| Sonnet 5 | $0.00017 | $0.00446 |
| Haiku 4.5 | $0.00009 | $0.00223 |
Grade A, and why
hierarchical-agent-files 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 12d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hierarchical Agent Files Scaffold
Trigger
- Use when a workspace needs a parent-plus-children agent-file hierarchy where each nested folder carries its own four-file contract and the parent carries the canonical progress-scope rule.
- Use when the single-workspace
agent-filesskill is not enough because two or more sibling nested workspaces must share a common parent mission and a common harness. - Do not use for a flat, single-folder contract; route to
agent-files. - Do not use for trees deeper than parent + direct children; grandchildren are out of scope in this version.
- Do not use to retrofit hierarchy onto an existing hand-edited parent that already has non-trivial content in its four files unless
overwrite=true.
Inputs
parent_dir: directory where the parent four-file contract is scaffoldedparent_mission: one- or two-sentence long-term mission statement written into the parentAGENT_GOAL.md; required so the contract is internally consistent on first read. It must not include reusable workflow rules, current state, next steps, or transient objectives.parent_objective: optional transient in-flight objective for the parentAGENT_PROGRESS.md; it must not define permanent mission, scope, policy, or success criteriaparent_name: short name used in child cross-references; defaults tobasename(parent_dir)with trailing slash strippedchildren: non-empty list of direct-child workspaces, each with:relative_dir: single path segment (no/, no.., not absolute)mission: child's one- or two-sentence long-term mission statement; it must stay within the parent mission and avoid reusable workflow/current-state detailsobjective: optional transient child in-flight objective
overwrite: when true, existing files are replaced through an explicit scaffold overwrite; otherwise compatible existing parent and child files are recorded infiles_skippedper node, immutableAGENT.mdfiles are verified rather than patched, and hierarchy changes or verifications run only after upstream and hierarchy compatibility checks pass
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 83 lines · 86 tokens per session scan A 6d7d8c102eba
hierarchical-agent-files is a skill published in the GitHub repository zhouyou-gu/skill-marketplace-template (5 stars, last pushed 19d ago), licensed MIT. It adds 86 tokens to every session and 2,229 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 2026-08-31.
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…