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.
git clone --depth 1 https://github.com/taylorleese/claude-toolzWrote 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/commands/taylorleese/claude-toolz/ask-llm)<a href="https://agentmods.dev/commands/taylorleese/claude-toolz/ask-llm"><img src="https://agentmods.dev/badge/commands/taylorleese/claude-toolz/ask-llm.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 5.1 | $0.00015 | $0.00536 |
| Opus 5 | $0.00008 | $0.00268 |
| Sonnet 5 | $0.00003 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
ask-llm 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 7d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get a second opinion from a non-Claude frontier model.
Invoke the ask-llm:ask-llm skill via the Skill tool. It owns the script invocation, provider configuration, and error handling.
Parsing $ARGUMENTS
$ARGUMENTS is [provider] [question], both optional:
- If the first word is
codex,agy,deepseek, orall, that selects the provider and the remainder is the question. - If the first word is not a provider name, the whole of
$ARGUMENTSis the question and the provider defaults tocodex— no API key required and the strongest choice for code. allmeans run every enabled provider concurrently in a single message, then summarize where they agree and disagree. All three are different vendors (OpenAI, Google, DeepSeek), so the disagreements are meaningful. Skip any provider listed inASK_LLM_DISABLED_PROVIDERS.status(orlist) means runask.py --listand show the readiness table instead of asking anything.- If
$ARGUMENTSis empty, ask for a general second opinion on the current work using the default provider.
Examples:
/ask-llm codex is this migration reversible?
/ask-llm all which caching strategy would you pick here?
/ask-llm does this error handling miss anything?
/ask-llm status
/ask-llm
codex and agy reason before answering, so they take about 5-7 seconds against DeepSeek's 1.4. That is expected — do not treat the delay as a hang.
Assembling the context
The skill reads context on stdin, so decide what to send before invoking it:
- If the user just referenced specific files or a diff, send those.
- Otherwise send the relevant part of the current conversation — the problem, the constraints, and what has already been tried.
- Write anything long to a scratch file and redirect it in rather than echoing inline.
Send enough to be useful and nothing sensitive: this leaves the machine for a third-party provider. Do not include secrets, credentials, or customer data.
After the skill returns, relay the response and add your own view — say where you agree, where you don't, and why. It is another model's opinion, not a verdict.
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.
- 7d ago First seen · 45 lines · 15 tokens per session scan A d23aaffd0ef0
ask-llm is a command published in the GitHub repository taylorleese/claude-toolz (3 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 536 once invoked, about $0.0001 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
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.