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 SiyaoZheng/GEZHI --skill gezhi-template-authorgit clone --depth 1 https://github.com/SiyaoZheng/GEZHIWrote 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/siyaozheng/gezhi/gezhi-template-author)<a href="https://agentmods.dev/skills/siyaozheng/gezhi/gezhi-template-author"><img src="https://agentmods.dev/badge/skills/siyaozheng/gezhi/gezhi-template-author/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/siyaozheng/gezhi/gezhi-template-author"><img src="https://agentmods.dev/badge/skills/siyaozheng/gezhi/gezhi-template-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 34 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 154 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 155 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00035 | $0.01747 |
| Opus 5.5 | $0.00014 | $0.00699 |
| Sonnet 5.5 | $0.00007 | $0.00349 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade A, and why
gezhi-template-author 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 2mo 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gezhi Template Author
Use this skill when maintaining reusable gezhi setup material rather than
configuring one user's project. The audience is future agents and advanced
users who need a reliable recipe for a project family.
Do not use this skill to connect an ordinary target project to gezhi. For
that job, use gezhi-project-setup. This skill only maintains the reusable
material that llms.txt and gezhi-project-setup point agents toward.
Template work includes:
- new example
gezhi.tomlfiles; - project-type setup docs;
- deterministic tik oracle scripts;
- producer wrapper templates;
- reusable prompts;
- updates to
llms.txt,docs/skills.md, README links, or skill content.
Design Principles
- The artifact is the control point. Each template must name one canonical artifact shape.
- Producer first. A template is incomplete unless it explains how the artifact is rebuilt from source.
- Tik and tok stay separated. Tik reviews the artifact; tok success is measured by runtime-audited source changes.
- Defaults should be safe for non-experts: narrow write scopes, protected generated dirs, dry-run validation before real heartbeats.
- One-prompt setup material must be usable by an agent that has never seen the
target project and by a user who cannot debug
gezhi.tomlby hand. - Templates must include install/verification steps and a failure path for missing commands, failed producers, missing artifacts, and failed doctor checks.
- Deterministic checks beat model review when they can reject failures clearly.
- Examples should be runnable from a clean checkout or should state exactly which target project files they expect.
Template Workflow
1. Define the Project Family
Write down:
- artifact kind: PDF, site, workbook, report, benchmark, package, model metric;
- expected source directories;
- generated directories;
- likely build tools;
- whether a deterministic tik oracle is possible;
- what the user can inspect directly.
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.
- 2mo ago First seen · 228 lines · 35 tokens per session scan A 0e7636ceeb06
gezhi-template-author is a skill published in the GitHub repository SiyaoZheng/GEZHI (42 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,747 once invoked, about $0.0001 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 2026-08-30.
gezhi-template-author compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gezhi-template-authorSiyaoZheng/GEZHI | Skill | 42 | 2mo ago | MIT | A | 35 | Claude Code, Codex |
| figure-styleaipoch/open-science | Skill | 5.5k | yesterday | Apache-2.0 | A | 91 | Claude Code, Codex |
| remote-compute-sshaipoch/open-science | Skill | 5.5k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| paper-narrativeaipoch/open-science | Skill | 5.5k | yesterday | Apache-2.0 | A | 58 | Claude Code, Codex |
| self-awarenessaipoch/open-science | Skill | 5.5k | yesterday | Apache-2.0 | A | 70 | Claude Code, Codex |
| figure-composeraipoch/open-science | Skill | 5.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| literature-reviewaipoch/open-science | Skill | 5.5k | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |