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 vinta/hal-9000 --skill differencegit clone --depth 1 https://github.com/vinta/hal-9000Wrote 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/vinta/hal-9000/difference)<a href="https://agentmods.dev/skills/vinta/hal-9000/difference"><img src="https://agentmods.dev/badge/skills/vinta/hal-9000/difference/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/vinta/hal-9000/difference"><img src="https://agentmods.dev/badge/skills/vinta/hal-9000/difference.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 | $0.00035 | $0.00334 |
| Opus 5.5 | $0.00014 | $0.00134 |
| Sonnet 5.5 | $0.00007 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00033 |
Grade A, and why
difference 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 13d 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.
What it actually says
Difference
The user wants a fast answer, not research. Invoking this skill is their explicit opt-out of any standing rule to check docs or search before answering: answer from what you already know.
Compare what the arguments name. With no arguments, compare the items just discussed; ask only when nothing comparable is there.
Lookups
Run one web search (WebSearch in Claude Code, web_search in Codex) only for an item you cannot identify at all, such as a tool released after your training or an unknown term, then answer. Being unsure of an item's latest version does not count. Use no subagents.
Answer
Keep it as short as the question allows, and let the items decide the shape. Spend the words on where they actually differ, not on what they share.
- Alternatives someone picks between (tools, approaches, patterns): give each one's pros and cons.
- Sentences: how each lands differently — tone, implication, what a reader infers.
- An answer that hinges on a version, price, or "latest" fact: add one line saying it is as of your training data.
The last line of the answer is still comparison: no verdict, no offer to dig deeper.
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.
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.
- 13d ago Changed 3db4b6bfbde1
- 22d ago First seen · 30 lines · 35 tokens per session scan A 7fe055da919c
difference is a skill published in the GitHub repository vinta/hal-9000 (139 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 334 once invoked, about $0.0001 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 2026-09-25.
Other skills, from other repositories
jarvis-setup
Use when helping someone install, configure, or debug a fresh clone of JARVIS (this repo) — especially "the mic doesn't work", "JARVIS says his language systems are down", any Firefox/browser question, login/auth failures, or Accessibility permission prompts. Carries facts about this project that were only learned by…
optimize-python-parallelism
Analyze and, when the task authorizes source optimization, refactor a concrete long-running Python entrypoint containing repeated independent work. Use for explicit Python speedup or parallelization requests and evidence-backed long-running entrypoints; skip ordinary Python edits, test execution alone, short scripts…
cirq
Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for…
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
scikit-bio
Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.
simpy
Build, inspect, test, and analyze bounded process-based discrete-event simulations with SimPy, including events, resources, interrupts, monitoring, replications, warm-up, and reproducible output analysis.