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/implementnpx skills add emdash-cms/emdash --skill implementgit 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 | $0.00035 | $0.01167 |
| Opus 5 | $0.00017 | $0.00583 |
| Sonnet 5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
implement 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement
A maintainer explicitly asked you to build the issue's requested change. Treat the issue body and directive as the specification. This lane is for enhancements and directed changes; do not invent a bug verdict or describe an enhancement as reproduced.
Delivery priorities
The working candidate is the deliverable; tests are evidence for it. TDD controls ordering for a confirmed bug, not how much of the run test construction may consume. Enhancements do not need a failing test first.
- Use an existing test file, helper, and configuration at the lowest layer that proves the requested behavior. One focused regression case is normally enough.
- Do not add a test configuration, package script, custom harness, or dependency inspection solely to make the change testable. Do not inspect
node_modulesunless the requested behavior depends on third-party internals. - If one test approach has not converged after three attempts or about ten minutes, stop using it. Choose a lower-level seam or implement the scoped change and report the test gap. For a confirmed bug, do not claim completion without a meaningful regression test; publish the partial candidate and state what is missing.
- 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.
Procedure
- Read
AGENTS.mdand the relevant implementation, tests, and contributor guidance before editing. - The harness installs dependencies and builds the base workspace before this turn. Do not run
pnpm install, the rootpnpm build, or a pre-edit lint baseline. - Choose the smallest final verification set before editing: the focused behavior test, affected package tests and typechecks, final lint, and a check-only formatter. Do not plan a monorepo-wide test suite when focused or package-level checks cover the changed behavior.
- Resolve ambiguity from existing APIs, sibling code, and backwards-compatible behavior. If a missing decision would materially change the public contract, stop and report it instead of guessing.
- Edit through
edit_fileandwrite_file. Keep the change scoped to the request. Do not modify.github/workflowsor generated Lingui catalogs. - Add the smallest behavior-level test that uses existing infrastructure. For a directed bug fix, follow the repository's failing-test-first rule within the test-construction limit above.
- Finish every candidate edit before final verification. Apply formatting and add the changeset now, when a published package changed. Follow
.changeset/README.md: write public CHANGELOG documentation with detail proportional to the impact, not a diff summary. - Run the planned final checks with
exec, once each on the final candidate. Fix failures caused by the change and rerun the affected check after editing. Do not hide failures with shell fallbacks. If a relevant failure remains, preserve the candidate and report it accurately instead of withholding the work from CI. - Call
publish_candidateafter the final checks, including when a check remains failing. The trusted tool commits and pushes only tobot/fix-<issue>through the issue-scoped Git proxy; never rungit commit,git push, or create a PR yourself. - Call
report_implementationexactly once. Setimplemented: trueonly after publication succeeds. Summarize the observable change and verification, not a bug verdict.
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 · 57 lines · 35 tokens per session scan A 6c8a0214781c
implement is a skill published in the GitHub repository emdash-cms/emdash (12,111 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 1,167 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.