verify

A read-only review procedure for deciding whether diagnosed behaviour is truly a software bug or an intentional design choice. It compares the code with its comments, documentation, tests, project instructions, and other uses.

In plain words
What is it for?
Use it after diagnosis to inspect the relevant implementation and supporting materials, then classify the behaviour as a bug or as working as designed.
Why use it?
Finding code that explains a symptom does not prove that the code is wrong. This check prevents unnecessary fixes for documented behaviour, misunderstandings, or incorrect API use.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/emdash-cms/emdash/verify
Any agent
npx skills add emdash-cms/emdash --skill verify
Clone the repo
git clone --depth 1 https://github.com/emdash-cms/emdash

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 895 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00895
Opus 5 $0.00016 $0.00447
Sonnet 5 $0.00007 $0.00179
Haiku 4.5 $0.00003 $0.00089

Measured 2d ago against content hash 36263edcfb8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify 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.

infra/emdash-bot/.flue/skills/verify/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify

Diagnose found code that explains the symptom. That does not make the code wrong. Plenty of EmDash issues describe behaviour that is intentional but under-documented, surprising at first glance, or a misuse of the API. Tell the difference -- fix runs only when you say bug.

You read code, comments, docs, tests, and AGENTS.md. You modify nothing. No edits, no test runs, no dev servers.

Environment

Pure inspection -- entirely VFS work. Use read_file, ls, grep, and code to cross-reference code, docs, and tests. Do not attach a container.

Do not

  • No edits, no git commit, no git push.
  • No GitHub writes. Read-only API GETs only.
  • No network beyond the clone and the proxy-signed GitHub API.
  • Touch no issue other than the one being investigated.

Procedure

  1. Re-read the diagnose output. The file, the line range, the prose. Hold it in mind as you cross-reference.
  2. Read the surrounding code, not just the line. Comments immediately above and below; the function's docstring/JSDoc; its name and signature (often documents intent); adjacent branches and other call sites.
  3. Cross-reference documentation. AGENTS.md and CONTRIBUTING.md for repo-wide rules (SQL safety, locale filtering, RBAC, request caching, query-count budget); docs/ for user-facing behaviour that may be intentional; the package README or top-level docstring.
  4. Cross-reference tests. An existing test asserting the current behaviour means it is intentional -- unless the test itself is wrong. Open it, read what it asserts and why. A test named for the diagnosed function is the strongest intent signal the repo has.
  5. Decide -- three verdicts only:
    • bug -- behaviour matches the code, the code does not match documented or clearly implied intent, and the reporter's expectation is reasonable. (Missing locale filter; off-by-one pagination; a 500 where a 404 belongs; a permission check admitting the wrong actor.)
    • intended-behavior -- behaviour matches the code, and the code matches documented intent. ({ items, nextCursor } not a bare array; the X-EmDash-Request CSRF header requirement; slugs unique per-locale not globally per migration 019; a maintainer-only endpoint returning 403 to authors.)
    • unclear -- docs are silent and intent cannot be inferred. Maybe a bug, maybe not; the maintainer decides.
  6. Resist two failure modes. Do not call intended-behavior just because a test exists -- a test asserting wrong behaviour is part of the bug. Do not call bug just because the reporter is upset -- frustration is not a verdict.
  7. Explain, with citations. One or two short paragraphs per verdict, citing the specific comment, doc section, or test by path. For intended-behavior, state the documented intent explicitly so the bot's comment can point the reporter at it ("I think this is by design -- see <doc> / <test> -- happy to revisit if you disagree"). For unclear, list what you would need to know to decide.

Read the full file on GitHub · 44 lines

Changes

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.

  1. 2d ago First seen · 44 lines · 33 tokens per session scan A 36263edcfb8e

Subscribe to this mod's changes

verify is a skill published in the GitHub repository emdash-cms/emdash (12,159 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 895 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.

Related

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.

EngDawood/emdash-claude-plugin · 52 tokens

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…

EngDawood/emdash-claude-plugin · 70 tokens

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.

EngDawood/emdash-claude-plugin · 56 tokens

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…

EngDawood/emdash-claude-plugin · 234 tokens

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.

EngDawood/emdash-claude-plugin · 71 tokens

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.

EngDawood/emdash-claude-plugin · 32 tokens