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 quan0715/open-press --skill openpress-collaborategit clone --depth 1 https://github.com/quan0715/open-pressWrote 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-collaborate)<a href="https://agentmods.dev/skills/quan0715/open-press/openpress-collaborate"><img src="https://agentmods.dev/badge/skills/quan0715/open-press/openpress-collaborate/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-collaborate"><img src="https://agentmods.dev/badge/skills/quan0715/open-press/openpress-collaborate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00920 |
| Opus 5 | $0.00014 | $0.00460 |
| Sonnet 5 | $0.00006 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
openpress-collaborate 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenPress Collaborate
This skill selects how an agent and user review authored-content changes. The Agent GUI carries instructions; Workbench renders Current and Proposed pages and collects Proposal feedback.
Choose A Mode
| Mode | Trigger | Source mutation |
|---|---|---|
| Answer | analysis or review without a requested change | none |
| Propose | non-trivial edit, preview, or writing judgment | review handoff only |
| Apply | explicit request to apply the current Preview | exact reviewed replacements |
| Direct | explicit review bypass, or a small mechanical edit | direct source edit |
Initial creation belongs to the format skill because new files have no useful before text. Use Propose for later revision.
Propose
- Read current source, workspace instructions, relevant writing/format skills, and related pending
@openpress-commentmarkers. - Do not edit authored
press/source. - Replace
.openpress/review/current.jsonwith the complete current proposal set:
{
"proposals": [
{
"path": "press/book/chapters/intro.mdx",
"before": "Exact current source text.",
"after": "Exact replacement text.",
"note": "Short reason for this change"
}
]
}
Each Proposal must target authored .mdx or .tsx under press/, use a non-empty exact unique before, contain the complete after replacement, and include one plain-language note. For insertion, include stable neighboring text in both values. Use an empty after for deletion. Order by path and source position.
Write only path, before, after, and note; Workbench may add feedback. Replace the whole handoff each pass—do not preserve ids, history, hashes, or superseded feedback.
Tell the user to open Changes in Workbench. Current and Proposed markers share the same note and feedback. Stop before editing source.
Refresh From Feedback
Read the current handoff before replacing it. Treat accept, reject, more-info, and free-text feedback as input, re-read current source, reconsider the complete change set, then write a fresh proposal file without copying old feedback.
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.
- 9d ago First seen · 82 lines · 28 tokens per session scan A 8250cb7a47db
openpress-collaborate is a skill published in the GitHub repository quan0715/open-press (14 stars, last pushed 10d ago), licensed MIT. It adds 28 tokens to every session and 920 once invoked, about $0.0001 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.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
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.