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 commands/kastheco/claude-plugins/verifygit clone --depth 1 https://github.com/kastheco/claude-pluginsWhat 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 | $0.00007 | $0.01219 |
| Opus 5 | $0.00003 | $0.00609 |
| Sonnet 5 | $0.00001 | $0.00244 |
| Haiku 4.5 | $0.00001 | $0.00122 |
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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/kas:verify - Verify Implementation
Tiered verification with early-exit. Validates both code quality AND plan completion.
Workflow
1. Check scope and determine relevant agents
git status
git diff --stat
git diff
If no changes (empty diff), report "Nothing to verify" and stop.
Analyze the diff to determine which Tier 1 agents are relevant:
| Change Pattern | Tier 1 Agents to Run |
|---|---|
| Any code changes | code-reviewer (always) |
| try/catch, error handling, catch blocks | + silent-failure-hunter |
Comments, docstrings, JSDoc, //, /*, """ |
+ comment-analyzer |
| Type definitions, interfaces, schemas, generics | + type-design-analyzer |
| Test files, describe/it/test blocks | + pr-test-analyzer |
Tier 1 agent selection by change type:
- Code changes → run relevant Tier 1 agents based on patterns above
- Markdown/docs only → skip Tier 1, proceed directly to Tier 2
- Config files only → code-reviewer only, then Tier 2
Important: Tier 2 (reality assessment) ALWAYS runs if there are any changes, because it validates plan completion - not just code quality.
2. Tier 1: Static Analysis (parallel, only relevant agents)
Launch only the relevant agents in parallel using the Task tool.
Agent - Code Review (kas): (run if any code changes)
"Run code review on the current git changes.
Read agent instructions at agents/code-reviewer.md (relative to plugin root)
Return structured findings with severity levels and overall assessment (APPROVED/NEEDS CHANGES/REJECTED)."
Agent - Silent Failure Hunter (pr-review-toolkit): (run if error handling changes)
"Check for silent failures in error handling.
Look for: empty catch blocks, swallowed exceptions, missing error propagation, try/catch without proper handling.
Return findings with severity levels."
Agent - Type Design Analyzer (pr-review-toolkit): (run if type/interface changes)
"Review type definitions, interfaces, and schemas in the changes.
Check for: overly permissive types, missing null checks, inconsistent naming, type safety issues.
Return findings with severity levels."
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.
- 2d ago First seen · 144 lines · 7 tokens per session scan A 091993416e62
verify is a command published in the GitHub repository kastheco/claude-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 1,219 once invoked, about $0.0000 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.