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 albatrossflyon-coder/claude-token-operator-kit --skill verifygit clone --depth 1 https://github.com/albatrossflyon-coder/claude-token-operator-kitWrote 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/albatrossflyon-coder/claude-token-operator-kit/verify)<a href="https://agentmods.dev/skills/albatrossflyon-coder/claude-token-operator-kit/verify"><img src="https://agentmods.dev/badge/skills/albatrossflyon-coder/claude-token-operator-kit/verify/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/albatrossflyon-coder/claude-token-operator-kit/verify"><img src="https://agentmods.dev/badge/skills/albatrossflyon-coder/claude-token-operator-kit/verify.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00060 | $0.00648 |
| Opus 5.5 | $0.00024 | $0.00259 |
| Sonnet 5.5 | $0.00012 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify: CC + Second-Model Cross-Check
Runs a second-opinion validation on a Claude output using Gemini as an independent checker. Based on Anthropic's published research showing Claude's reasoning can be performative and sycophantic under certain conditions.
When to Use
- CC produced an analysis, plan, or recommendation you're about to act on
- You suspect CC agreed with you too easily
- CC made factual claims about tools, APIs, or external systems
- High-stakes decisions (architecture, spending, strategy)
Trigger Phrases
/verify- "double-check this with Gemini"
- "run a second opinion"
- "cross-check that"
Process
Step 1: Extract the claim or output
Identify what needs verification:
- A specific factual claim ("X tool does Y")
- A plan or recommendation
- An analysis result
- Code correctness
Step 2: Formulate the Gemini prompt
Send this to Gemini (Gemini CLI, or any Gemini interface you have set up):
Evaluate this response for factual accuracy. Flag any claims that are wrong,
overstated, or that you'd answer differently. Be specific about what's off
and why. Do not summarize what's correct: only flag what's wrong or uncertain.
[PASTE CC OUTPUT HERE]
Step 3: Reconcile
Compare Gemini's flags against CC's output:
- If Gemini flags something CC was confident about → treat as uncertain, investigate
- If Gemini agrees → confidence increases (but still not 100%)
- If they contradict → dig into the specific claim with a direct question to both
Step 4: Update or stand pat
- If verification finds an error: correct the output before acting
- If no flags: proceed with higher confidence, note it was verified
The Root Problem This Solves
From Anthropic's interpretability research:
- Claude's "I don't know" circuit gets overridden when it recognizes a topic
- Step-by-step reasoning shown to you is often performative: doesn't match internal calculations
- If you hint at an answer, Claude reverse-engineers fake reasoning to agree
- Internal momentum makes mid-response correction hard
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.
- 1mo ago First seen · 75 lines · 60 tokens per session scan A 44e4c22208e6
verify is a skill published in the GitHub repository albatrossflyon-coder/claude-token-operator-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 648 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…