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 iowarp/clio-kit --skill software-environmentgit clone --depth 1 https://github.com/iowarp/clio-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/iowarp/clio-kit/software-environment)<a href="https://agentmods.dev/skills/iowarp/clio-kit/software-environment"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/software-environment/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/iowarp/clio-kit/software-environment"><img src="https://agentmods.dev/badge/skills/iowarp/clio-kit/software-environment.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 | $0.00044 | $0.01000 |
| Opus 5.5 | $0.00018 | $0.00400 |
| Sonnet 5.5 | $0.00009 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
software-environment 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 9d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Environments
Two servers answer overlapping questions about available software, and they answer different ones. Reaching for the wrong one gives a confidently wrong answer rather than an error.
There is no module_load, on purpose
The lmod server discovers environments and manages saved collections. It reports what a machine has; it cannot change what is loaded.
That is deliberate rather than missing. A module load performed inside a tool
call runs in a child process with a copied environment, and the change dies when
that child exits. A tool doing it would report success while nothing was loaded
for anything that followed, which is a silently wrong answer rather than an
error anyone would see. The tools that used to do this were removed for exactly
that reason.
To get software into a run, resolve it with clio-spack:spack_locate and pass
output.load_spec to clio-jarvis:jarvis_run in the top-level spack_specs argument, which does
persist for the execution. See cluster-run.
Which tool answers which question
"What is loaded right now?" — clio-lmod:module_list. Reflects the
server's own environment, which is only meaningful if something loaded it there.
"Does this machine offer X?" — clio-lmod:module_avail with a name pattern.
It searches what is currently visible in MODULEPATH.
"Really, does it offer X anywhere?" — clio-lmod:module_spider. Searches the
entire module tree, including modules hidden behind a compiler or MPI hierarchy
that module_avail cannot see until a prerequisite is loaded. When module_avail
comes back empty, this is the one that finds it.
"What does this module actually set?" — clio-lmod:module_show. Use it before
depending on a module for anything: it reveals the prerequisites and the
variables it sets.
"Is this package installed under Spack?" — clio-spack:spack_find. Only sees
what is already built. Zero matches is a successful result, not an error.
"Does a recipe for it exist at all?" — clio-spack:spack_search. Broader than
spack_find: it answers whether a recipe exists, in which repo, and whether it
happens to be installed. Use it before concluding software is unavailable.
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.
- 9d ago First seen · 90 lines · 44 tokens per session scan A e83f3f890a83
software-environment is a skill published in the GitHub repository iowarp/clio-kit (30 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 44 tokens to every session and 1,000 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 2026-10-08.
Other skills, from other repositories
bioprobench
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.
evo-memory
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory MI (feasible/unsuccessful directions) and Experimentation Memory ME (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after…
raindrop-mcp
Connect Raindrop.io to your AI assistant with a simple MCP server. Use it to organize, search, and manage bookmarks with natural language.
onescience-orchestrator
A task coordinator for OneScience that turns a user’s goal into a tracked plan and assigns parts of the work to suitable specialist tools.
sota-management
4-level SOTA performance tracking for VibeCodeHPC. Use when checking or updating best performance records.
authoring-gradle-builds
Authoring and modifying Gradle build logic, including settings, plugins, dependencies, tasks, conventions, and upgrades. Activate when build files or plugins must change; use using-gradle for inspection or execution without build-definition edits.