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 respira-press/agent-skills-wordpress --skill wordpress-editing-safetygit clone --depth 1 https://github.com/respira-press/agent-skills-wordpressWrote 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/respira-press/agent-skills-wordpress/wordpress-editing-safety)<a href="https://agentmods.dev/skills/respira-press/agent-skills-wordpress/wordpress-editing-safety"><img src="https://agentmods.dev/badge/skills/respira-press/agent-skills-wordpress/wordpress-editing-safety/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/respira-press/agent-skills-wordpress/wordpress-editing-safety"><img src="https://agentmods.dev/badge/skills/respira-press/agent-skills-wordpress/wordpress-editing-safety.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00087 | $0.01100 |
| Opus 5.5 | $0.00035 | $0.00440 |
| Sonnet 5.5 | $0.00017 | $0.00220 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
wordpress-editing-safety 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WordPress Editing Safety
These rules are the difference between a tool the user trusts and a tool that breaks their site. They are the same rules Respira sends every agent as its core rules, on every channel; this skill explains how to apply them.
1. Read before you write
Start with respira_get_site_context and respira_get_builder_info, so you know which page builder you are writing for. Then find the exact element with respira_find_element before you change it. If the target is ambiguous, ask one short question rather than guess.
2. Live pages go through a duplicate
On a published page or post, Respira puts the edit on a draft duplicate for you (it creates one, or points you to the one already open) unless the site owner has turned on direct editing, so calling the duplicate tool first is optional; a person approves the duplicate before it goes live.
What that means in practice:
- Edit the page the user named. If it is published, the write lands on a draft duplicate and the answer tells you which one.
- Give the user the preview link from the answer, so they can see the change before it goes live.
- Call
respira_create_page_duplicateyourself only when you want the copy before the first edit, for example to hand a preview to a client or to stage several changes together. - Pass
forceandconfirm_live_editonly when the person asked for a live edit. The site's own setting decides whether that is allowed.
3. Snapshots are automatic
Page and post writes save a snapshot before they run, so a change is one respira_restore_snapshot away. You do not need to take one by hand. For a change that spans several pages, bracket it with respira_begin_session and respira_end_session, so respira_restore_session can undo all of it at once.
4. Verify every write
A saved write and a correct page are different things. Every write answer carries trace fields; read them:
partial_write: truemeans some of the change did not land.validator_warningslists what the validator found.render_validator_pass: falsemeans the database accepted the change but the rendered page does not match.
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 · 68 lines · 87 tokens per session scan A ee9c31552322
wordpress-editing-safety is a skill published in the GitHub repository respira-press/agent-skills-wordpress (48 stars, last pushed 3d ago), licensed MIT. It adds 87 tokens to every session and 1,100 once invoked, about $0.0003 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 2026-10-15.
Other skills, from other repositories
inbox-zero
Scan your support inbox and batch-process tickets with quick actions (reply, tag, assign, close).
ticket-summarize
Summarize a support ticket thread into key points and action items.
weekly-digest
Generate a weekly support digest and post it to Slack.
zoho-desk-triage
Pull open tickets from Zoho Desk and triage by priority and department.
baoyu-wechat-summary
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory…
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.