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/apurvbazari/claude-plugins/verifynpx skills add ApurvBazari/claude-plugins --skill verifygit clone --depth 1 https://github.com/ApurvBazari/claude-pluginsWrote 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/apurvbazari/claude-plugins/verify)<a href="https://agentmods.dev/skills/apurvbazari/claude-plugins/verify"><img src="https://agentmods.dev/badge/skills/apurvbazari/claude-plugins/verify.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00057 | $0.01534 |
| Opus 5 | $0.00028 | $0.00767 |
| Sonnet 5 | $0.00011 | $0.00307 |
| Haiku 4.5 | $0.00006 | $0.00153 |
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 3d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Skill — Independent Feature Evaluation
You are orchestrating an independent verification of features against the project's feature list. This implements the evaluator layer from Anthropic's harness design — a separate agent that judges purely on outcomes, not implementation reasoning.
Guard
Read docs/feature-list.json in the project root. If not found:
No feature list found. Create
docs/feature-list.jsonwith your project's features to enable verification.See the harness design reference for the expected format.
Stop and do not proceed.
Step 1: Determine Mode
Parse the command arguments:
/onboard:verify(no args) — verify all features wherepassesisfalse/onboard:verify F001— verify a single feature by ID/onboard:verify --sprint 1— verify all features in Sprint 1 and check sprint contract
Read docs/feature-list.json and identify the target features based on the mode.
Report to the developer:
Verification mode: [all incomplete / feature F001 / Sprint 1] Features to test: [N] Strategy: [verificationStrategy from onboard-meta.json]
Starting independent evaluation...
Step 2: Load Verification Context
Read .claude/onboard-meta.json to get the verificationStrategy (browser-automation, api-testing, cli-execution, test-runner, or combination).
If sprint mode, also read docs/sprint-contracts/sprint-N.json for the negotiated criteria.
Step 3: Spawn Feature Evaluator
Spawn the feature-evaluator agent with:
- The list of target feature IDs
- The verification strategy
- The sprint contract (if sprint mode)
The agent runs in worktree isolation (isolation: worktree) — it gets a throwaway copy of the project and is strictly read-only (it never writes docs/feature-list.json or a report file; any write in its worktree is discarded). It tests the running application and returns structured verdicts ({id, passes, evidence} per feature) plus the full verification-report body as text. You (verify) perform every write.
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.
- 3d ago First seen · 140 lines · 57 tokens per session scan A 22e615216039
verify is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 27d ago), licensed MIT. It adds 57 tokens to every session and 1,534 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
cross-platform
Cross-platform development patterns for macOS, Windows, and Linux.
shell-scripting
Shell scripting best practices for cross-platform CLI tools.
c-notify
Send native macOS notification center alerts from the command line using terminal-notifier.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.