Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/quan0715/open-pressnpx agentmods add skills/quan0715/open-press/openpress-upgradeWrote 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/quan0715/open-press/openpress-upgrade)<a href="https://agentmods.dev/skills/quan0715/open-press/openpress-upgrade"><img src="https://agentmods.dev/badge/skills/quan0715/open-press/openpress-upgrade/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/quan0715/open-press/openpress-upgrade"><img src="https://agentmods.dev/badge/skills/quan0715/open-press/openpress-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 MCP Rug Pull · line 38 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Agent Snooping · line 113 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 138 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 Excessive Agency · line 216 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00052 | $0.01587 |
| Opus 5 | $0.00026 | $0.00794 |
| Sonnet 5 | $0.00010 | $0.00317 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
openpress-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 9d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPress Upgrade
openpress-upgrade owns framework package upgrades and workspace migrations.
Use openpress for command/source-boundary routing, then use this skill for
the upgrade and migration workflow.
Responsibilities
- Detect installed and target OpenPress versions.
- Refresh framework packages and installed OpenPress skills after confirmation.
- Select applicable migration docs from the OpenPress repo.
- Scan workspace source before editing.
- Generate and implement migration plans from the docs.
- Run migration QA checkpoints in a loop until all pass or a blocker needs user input.
Source Boundaries
Use the source/generated boundary from openpress. During migration, edit only:
press/- root
package.jsonandopenpress/settings.json - project-owned local skill files in
.agents/skills/ - project config explicitly named by a migration doc
Do not hand-edit node_modules/, public/openpress/, dist-react/,
.deploy/, .openpress/, .turbo/cache/, or installer-managed
.claude/skills/ links.
Workflow
0. Resolve The CLI Command
Use the workspace's local OpenPress CLI. Do not use npx open-press; open-press
is a binary name, not the npm package name.
Use one of these forms:
open-press <command> .
npm run openpress:skills
node node_modules/@open-press/core/engine/cli.mjs <command> .
Prefer the core CLI path in workspaces that only install @open-press/core.
Use the open-press binary only when @open-press/cli is installed and
node_modules/.bin/open-press exists.
1. Inspect
Run:
git status --short
node node_modules/@open-press/core/engine/cli.mjs doctor . --json
Record:
- current
@open-press/coreversion; - target/latest version from doctor;
- installed and tracked skills, all lockfile sources, missing canonical skills, and broken or missing agent links;
- unrelated dirty files that must not be touched.
Doctor is informational and exits 0 even when stale. If latest version cannot be checked, report the network limitation and do not guess the migration range.
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.
- 9d ago First seen · 220 lines · 52 tokens per session scan A 8148b327e6bc
openpress-upgrade is a skill published in the GitHub repository quan0715/open-press (14 stars, last pushed 11d ago), licensed MIT. It adds 52 tokens to every session and 1,587 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
emdash-cli
Use the EmDash CLI to manage content, schema, media, and more. Use this skill when you need to interact with a running EmDash instance from the command line — creating content, managing collections, uploading media, generating types, or scripting CMS operations.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
investigate
Investigate a single EmDash issue end to end -- classify, choose a repro path, reproduce, diagnose, verify, and (only on an explicit maintainer fix directive) fix and confirm. Every verdict carries its evidence.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
repro-public
Reproduce a bug in the public-facing rendered site (not the admin). Attach a container, start the demo dev server, drive public routes with agent-browser, and capture the reproduction as screenshots plus a replayable transcript.
verify
Decide whether the diagnosed behaviour is actually a bug or the code doing what it was designed to do. This is the gate that guards the fix stage.