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/jkheadley/instar/instar-devnpx skills add JKHeadley/instar --skill instar-devgit clone --depth 1 https://github.com/JKHeadley/instarWrote 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/jkheadley/instar/instar-dev)<a href="https://agentmods.dev/skills/jkheadley/instar/instar-dev"><img src="https://agentmods.dev/badge/skills/jkheadley/instar/instar-dev.svg" alt="Measured on agentmods" 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 | $0.00091 | $0.05440 |
| Opus 5 | $0.00046 | $0.02720 |
| Sonnet 5 | $0.00018 | $0.01088 |
| Haiku 4.5 | $0.00009 | $0.00544 |
Grade A, and why
instar-dev 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 5d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/instar-dev
Audience: this skill is for the instar-developing agent (Echo, or any agent assigned instar-dev responsibilities). It is NOT a user-facing skill. End users of instar should never invoke /instar-dev and will never see it in their workflow — it runs at the infrastructure-developer layer, not the per-user application layer. The enforcement hooks on the instar repo ensure the instar-developing agent goes through this skill for every change, but end users never encounter it.
Throughout this document, "the agent," "the instar-dev agent," or the imperative voice ("do this," "produce that") refer to the instar-developing agent, not the end user.
The skill for changing anything in the instar source tree.
Generic /build is the right tool for most projects. This skill is what the instar-developing agent uses when changing instar itself — the infrastructure every instar-powered agent inherits. Because those changes propagate to every agent and every user the moment they ship, the blast radius is structurally larger than any single project. This skill exists to make "careful" the default, not the exception.
When the instar-dev agent uses this skill
The instar-dev agent invokes /instar-dev before:
- Modify any file under
src/in the instar repo. - Add or change a hook, skill, job, template, scaffold, or route that ships with instar.
- Change behavior of a gate, sentinel, watchdog, recovery path, dispatcher, or anything else that makes a decision about agent behavior or information flow.
- Ship any fix, however small, that will be broadcast to the install base.
If the agent is only editing a markdown file that doesn't affect runtime behavior, the skill is still the correct entry point but the side-effects review will quickly conclude "documentation-only, no runtime surface" — which is a valid conclusion, not a skip.
The phases
The skill runs six structured phases. Each phase has clear success criteria. You cannot skip a phase — the enforcement hooks verify artifacts from every phase before a commit is allowed.
What ships with it
4 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.
- 5d ago First seen · 235 lines · 91 tokens per session scan A db4ad00e8576
instar-dev is a skill published in the GitHub repository JKHeadley/instar (77 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 5,440 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
skill-ledger
Skill 安全状态查看、风险暴露审查、用户决策、快速扫描认证与可选深度扫描。支持用户主动查看或扫描单个/全部 Skill；当用户要求 agent 安装 Skill 且安装成功后，必须自动对最终本地目录执行快速扫描认证。.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
pr-body
分析当前分支的全部变更，自动生成或更新 PR 标题和正文。聚焦内容质量：解释 why、归纳 what、标注测试方式，遵循 anolisa 项目 PR 模板规范。适用于新建 PR 前生成描述，或已有 PR 需要更新描述。.
install-openclaw
Install and configure OpenClaw non-interactively with Alibaba Cloud Model Studio. Use when the user asks to install OpenClaw, configure Aliyun Bailian/Model Studio/DashScope credentials, choose pay-as-you-go, Coding Plan, or Token Plan billing, set Base URL/model config, optionally configure DingTalk, start the local…
agentsight-bugfix
AgentSight fix issues 流程。了解问题 → 复现验证 → 根因分析 → 编码修复 → 验证修复，五阶段标准化调试迭代循环。确保 AI agent 遵循最小改动、逐轮验证的修复规范。.