EmDash is a content management system for creating and managing websites, built with TypeScript and Astro and deployable on Cloudflare or Node.js with SQLite. It is for site owners and developers who want WordPress-like administration, templates, and plugins without PHP or separate hosting.
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 emdash-cms/emdash --skill adversarial-reviewergit clone --depth 1 https://github.com/emdash-cms/emdashWrote 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/emdash-cms/emdash/adversarial-reviewer)<a href="https://agentmods.dev/skills/emdash-cms/emdash/adversarial-reviewer"><img src="https://agentmods.dev/badge/skills/emdash-cms/emdash/adversarial-reviewer/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/emdash-cms/emdash/adversarial-reviewer"><img src="https://agentmods.dev/badge/skills/emdash-cms/emdash/adversarial-reviewer.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 | $0.00072 | $0.00811 |
| Opus 5.5 | $0.00029 | $0.00324 |
| Sonnet 5.5 | $0.00014 | $0.00162 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
adversarial-reviewer 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial code review
Look for defects that survive an ordinary review. Treat the implementation's assumptions as claims to verify, while keeping every finding tied to evidence.
Establish the review boundary
- Identify the exact diff, branch, pull request head, or files under review.
- Read the surrounding code needed to understand data flow and invariants.
- Check repository instructions and the tests that define expected behavior.
- Compare the change with its stated purpose. Trace the scenario and configuration from the issue, discussion, or accepted design it addresses through the real code, and treat each claim in the description and changeset as something to verify.
- Separate defects introduced by the reviewed change from unrelated observations. Report an out-of-scope issue only when it materially affects the change's safety.
Do not modify code, post a review, or expand the review target unless the user asks.
Hunt for failures
Choose the checks that fit the change instead of mechanically applying every category.
- Logic and boundaries: empty and single-item inputs, pagination edges, invalid state transitions, locale handling, Unicode, maximum values, and repeat invocation.
- Errors and cleanup: swallowed failures, partial cleanup, misleading status codes, exposed internals, missing timeouts, and unbounded retries.
- State and concurrency: stale reads, lost updates, time-of-check/time-of-use races, duplicate delivery, non-idempotent retries, leaked listeners, and shared mutable state.
- Authorization and trust: missing permission checks, confused caller identity, CSRF, unsafe redirects, injection, path traversal, secret exposure, and trust transferred across a boundary without validation.
- Data integrity: partial writes, migration restart behavior, dialect differences, uniqueness assumptions, destructive cascades, and old/new version compatibility.
- Resources and performance: unbounded collections, repeated round trips, retained resources, logged-out hot-path regressions, and work that scales with attacker-controlled input.
- Scope: the same defect left in place elsewhere, such as sibling call sites, other storage backends or render paths, and data already stored in the old shape.
- Interfaces: exported types, generated schemas, generated types, and documentation that no longer match the new behavior.
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.
- 4d ago Changed · +3 lines · +10 tokens per session ce435bc59caf
- 1mo ago Changed · -67 lines · -9 tokens per session fca88cbcacdd
- 1mo ago First seen · 123 lines · 71 tokens per session scan A b14256841a3e
adversarial-reviewer is a skill published in the GitHub repository emdash-cms/emdash (13,868 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 811 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 2026-08-30.
Other skills, from other repositories
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
pr-review
Review Cool Workflow pull requests or branch diffs. Use when Codex must inspect code changes for bugs, regressions, FreeBSD/POLA violations, missing tests, generated artifact drift, release-contract risk, or CI implications, and return findings first with file/line citations.
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
code-review
Reviews code for bugs, security issues, and best practices.
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.