verify

A freshness checker for claims that can become outdated, such as software versions, end-of-life dates, package releases, container tags, and AI model availability. It uses primary sources and can run automatically before file edits or manually for a topic.

In plain words
What is it for?
Use it to check current versions, support dates, dependency status, GitHub Action references, Kubernetes API versions, image tags, or model deprecations.
Why use it?
It reminds you to verify time-sensitive technical facts instead of relying on old information.

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/raisedadead/claude-code-plugins/verify
Any agent
npx skills add raisedadead/claude-code-plugins --skill verify
Clone the repo
git clone --depth 1 https://github.com/raisedadead/claude-code-plugins

Made for: Claude Code, Codex.

Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00133 $0.01710
Opus 5 $0.00067 $0.00855
Sonnet 5 $0.00027 $0.00342
Haiku 4.5 $0.00013 $0.00171

Measured yesterday against content hash ad2c50fc7bae, 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 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- JSON APIs: `Bash` + `curl -s <url>`, so you read raw JSON. `WebFetch` summarises JSON, and a summary can hallucinate.
plugins/dossier/skills/verify/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ds:verify — empirical freshness check

Two surfaces, one rule: read the primary source's raw bytes.

Surface 1 — PreToolUse hook (auto)

Wired in hooks/hooks.json. Fires on Edit | Write | MultiEdit, and only in a repo that has a .scratchpad/dossier/ directory — elsewhere it exits 0 without scanning. Scans content against the pattern registry in hooks/verify_patterns.py and the authority catalog in hooks/verify_authorities.py (140+ aliases, 34 Docker images, 31 AI models). Covers language/runtime/OS/distro/database EOL, container-image EOL, GitHub Action SHA pinning, k8s deprecated apiVersions, npm/PyPI/Cargo/RubyGems/Go-mod outdated packages, and AI-model deprecation. Full coverage matrix + per-source cheatsheet → references/authorities.md.

Non-blocking by design — emits a stderr reminder plus additionalContext. Per-session dedup. Operator escape: # verify-skip: <ruleName> on or near the line.

Cache at <cwd>/.scratchpad/.verify-cache/ (24h TTL on registries, 30d on resolved SHAs). Offline = silent skip.

Surface 2 — /dossier:verify [<topic>] (manual, generic)

No pattern lock-in: the model classifies an arbitrary freshness claim and routes it to the right primary source.

Steps

  1. Identify claims. From $ARGUMENTS when provided, else every freshness-sensitive claim in the previous assistant message. Freshness-sensitive = the answer could plausibly have changed since the training cutoff.
  2. Classify each claim into one of these buckets:
    • Version / LTS / EOL of language, OS, distro, database, runtime → endoflife.date/api/v1/products/<slug>
    • Package latest → ecosystem registry (npm/PyPI/crates/RubyGems/Hex/Packagist/Go proxy/Maven Central/Homebrew)
    • GitHub release / tag / SHAapi.github.com/repos/<owner>/<repo>/releases/latest or /git/refs/tags/<tag>
    • CLI flag / subcommand → vendor docs (search official site)
    • API endpoint / schema → vendor docs / OpenAPI spec
    • AI model identifier → vendor deprecation page (OpenAI/Anthropic/Google/Mistral/Meta)
    • Framework / library API → official docs (search) or release notes
    • License / SPDX identifierspdx.org/licenses/
    • Standard / RFC → ietf.org / w3.org
    • Anything else freshness-sensitive → WebSearch first, then WebFetch the top primary source.
  3. Query the authority.
    • JSON APIs: Bash + curl -s <url>, so you read raw JSON. WebFetch summarises JSON, and a summary can hallucinate.
    • HTML docs: WebSearch then WebFetch, quoting the exact text you compared against.
    • GitHub: gh api <path> over WebFetch on github.com.
  4. Compare exact field values. Pull the specific field (releases[].name, info.version, crate.newest_version, …) and compare it against the claim's literal value. The comparison is field-to-value, not prose-to-impression.
  5. Render verdict table.

Read the full file on GitHub · 99 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 99 lines · 133 tokens per session scan A ad2c50fc7bae

Subscribe to this mod's changes

verify is a skill published in the GitHub repository raisedadead/claude-code-plugins (2 stars, last pushed 6d ago), licensed ISC. It adds 133 tokens to every session and 1,710 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens