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/hodstack/hodstack/deps-upgradenpx skills add hodstack/hodstack --skill deps-upgradegit clone --depth 1 https://github.com/hodstack/hodstackWhat 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 | $0.00058 | $0.01493 |
| Opus 5 | $0.00029 | $0.00746 |
| Sonnet 5 | $0.00012 | $0.00299 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
deps-upgrade 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deps Upgrade
Raise each dependency of this project to a newer version, one step at a time, and stop at the first step that breaks the tests.
1. Read the project
Read .hod/PROJECT.md for the command that installs the dependencies and the command that runs the tests.
Find each manifest at the top of the project. Section 3 names the command of each manifest.
Run git status --short. Stop when a file carries a change, and ask the user to commit that change first.
2. Take the baseline
Write no test during this work. A test that you write now covers the code that you changed, thus it shows no regression.
Run the test command that .hod/PROJECT.md names before you change a file. Decide this step from the output of that command only. Read no test file to decide it, and judge no test by its value, because a test that the framework wrote is a test and a test that asserts a constant is a test.
When a test fails, stop and raise no package. Name each test that failed from the output of the command. Say that the failure came before this work, thus the tests can show no regression. Give the report of section 8, and say that you raised no package, because the first list is empty. Ask the user nothing and write no commit.
When the test command does not exist, or when the command runs zero tests, tell the user that you found no test and that no test can show a regression, then ask the user to continue or to stop. Wait for the answer.
3. The command of each manifest
| Manifest | Report | Raise one package | Align the manifest |
|---|---|---|---|
composer.json |
composer outdated --direct |
composer require <package>:^<version> --with-all-dependencies |
composer bump |
package.json |
npm outdated |
npm install <package>@^<version> |
npm update --save |
Cargo.toml |
cargo upgrade --dry-run --incompatible |
cargo add <package>@<version> |
cargo upgrade |
pyproject.toml |
uv tree --outdated |
uv add <package>@<version> |
uv-bump |
go.mod |
go list -m -u all |
go get <package>@<version> |
go mod tidy |
What ships with it
1 file 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.
- 2d ago First seen · 80 lines · 58 tokens per session scan A 1a51f3f6c4ee
deps-upgrade is a skill published in the GitHub repository hodstack/hodstack (54 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,493 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 2026-08-30.
Other skills, from other repositories
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。.
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
systematic-debugging
Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.
mcp-builder
MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具，让 AI 助手连接外部能力.