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/emdash-cms/emdash/fixnpx skills add emdash-cms/emdash --skill fixgit clone --depth 1 https://github.com/emdash-cms/emdashWhat 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 | $0.00044 | $0.02146 |
| Opus 5 | $0.00022 | $0.01073 |
| Sonnet 5 | $0.00009 | $0.00429 |
| Haiku 4.5 | $0.00004 | $0.00215 |
Grade A, and why
fix 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 yesterday.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix
You are here because a maintainer issued a fix directive, verify returned bug, diagnose pinned the cause with at least medium confidence, and diagnose rated the fix mechanical or clear-best-option. Diagnose handed you a proposed fix -- a concrete plan naming the file and the change. Implement that plan, prove it works, and leave the change verified. The hard reasoning is done; do not re-litigate the diagnosis unless reading the code convinces you it is wrong (then abandon -- see below).
What your output is, and is not. You are not merging and not opening a PR. The trusted publish_candidate tool commits and pushes your change to the issue's bot/fix-<n> candidate branch through an issue-scoped Git proxy; that triggers a preview build the workflow posts to the issue. Only after the reporter confirms does a draft PR open, and a maintainer reviews before anything reaches main. The target is a correct, conventions-respecting change that makes the repro test pass. Publish a useful candidate even when a check remains failing, and report the failure accurately so CI and the maintainer can assess it. Do not gold-plate, expand scope, or refactor beyond the diagnosed bug.
Delivery priorities
The working candidate is the deliverable; the regression test is focused evidence. TDD controls ordering, not how much of the run test construction may consume.
- Reuse reproduce's evidence and the repository's existing test infrastructure. One focused case at the lowest layer that proves the same defect is enough.
- Do not add a test configuration, package script, custom harness, or dependency investigation solely to reproduce the bug. Do not inspect
node_modulesunless diagnose identified third-party behavior as the cause. - If the regression test has not converged after three attempts or about ten minutes, the test is at the wrong layer. Switch to a smaller seam. If no meaningful regression test fits existing infrastructure, publish the partial candidate, report the gap, and do not claim the bug fixed.
- Protect the final fifteen minutes for metadata, one verification pass,
publish_candidate, and reporting. Stop optional investigation before that window. - Update the public plan after the first source edit and when moving from editing to verification or publication. Do not leave it on an obsolete test step.
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.
- yesterday First seen · 96 lines · 44 tokens per session scan A c2a7542392e8
fix is a skill published in the GitHub repository emdash-cms/emdash (12,111 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 2,146 once invoked, about $0.0002 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
wordpress-plugin-to-emdash
Port a WordPress plugin to EmDash CMS. Use this skill when asked to migrate, convert, or port a WordPress plugin, theme functionality, or custom post type to EmDash. Provides concept mapping and implementation patterns.
building-emdash-site
Build and customize EmDash CMS sites on Astro. Use when creating pages, defining collections, writing seed files, querying content, rendering Portable Text, setting up menus/taxonomies/widgets, configuring deployment, or any task involving an EmDash-powered Astro site. Assumes basic Astro knowledge but provides all…
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.
emdash-github-actions
Sets up GitHub Actions CI/CD workflows for EmDash plugins — TypeScript type-checking, ESLint linting, Vitest testing, npm publishing, and automated releases. ALWAYS use this skill when a user wants to create, add, set up, or configure GitHub Actions, CI/CD, automated checks, or deployment workflows for an EmDash…
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.
agent-browser
Browser automation for testing and verification. Use when you need to interact with web UIs, verify visual changes, fill forms, or capture screenshots.