Borrowing it
Nothing to install: this file belongs to gevico/cosim-gpu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gevico/cosim-gpu/main/.agents/skills/cosim-gpu-info-gathering/SKILL.mdgit clone --depth 1 https://github.com/gevico/cosim-gpuWrote 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/gevico/cosim-gpu/cosim-gpu-info-gathering)<a href="https://agentmods.dev/skills/gevico/cosim-gpu/cosim-gpu-info-gathering"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-info-gathering/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/gevico/cosim-gpu/cosim-gpu-info-gathering"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-info-gathering.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 | $0.00090 | $0.01708 |
| Opus 5.5 | $0.00036 | $0.00683 |
| Sonnet 5.5 | $0.00018 | $0.00342 |
| Haiku 4.5 | $0.00009 | $0.00171 |
Grade A, and why
cosim-gpu-info-gathering 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 11d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cosim Information Gathering
Use this skill before broad log review, prior conversation scans, or cross-artifact summaries. Its job is to build a compact, attributed evidence map that other skills can reason from.
Source Order
Prefer archived artifacts over chat memory and live output:
- Matrix files:
matrix.final.tsv,matrix.tsv - Per-row verdicts:
tests/*/verdict.json - Provenance:
patch/binary-provenance.txt - Logs:
logs/gem5.log,logs/qemu.log, and vHost logs stored underlogs/guest/**/*.log - Runner metadata and vHost scripts
- Prior conversation records, only when the task is explicitly about process history or skill behavior
Every extracted fact must retain source file, line number when available, and the table or rule that produced it.
Evidence Preservation
Preserve raw evidence before optimizing the conversation. Token savings belong to what the agent reads and quotes, not to what a diagnostic run records.
For each test row, keep complete archived logs when the runner can provide them:
logs/gem5.loglogs/qemu.log- vHost logs stored under
logs/guest/**/*.log - exact command, environment, verdict, matrix row, build hash, and source fingerprint
Compact summaries are indexes over raw evidence. They must not be the only copy of a diagnostic observation unless the observation was never available in raw form.
Run Isolation
Keep each evidence intake tied to one explicit source set. Do not mix session records, live command output, and artifact summaries from different task turns unless the output names each source and range.
For session extracts, record the exact session path, start line, end line, whether tool output was included, and the text limit used. For artifact audits, record the artifact root and generated table directory. A later review should be able to tell whether two rows came from the same evidence intake or from different test rounds.
Bounded Reads
Do not scan home directories, token stores, or unrelated session trees. When a
conversation record is required, identify the exact session file first and parse
only user, assistant, command, and command-output summaries needed for the task.
Use .agents/skills/cosim-gpu-info-gathering/scripts/codex_session_extract.py
when available. Do not use head, plain rg, or broad filesystem search on
JSONL session records.
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.
- 11d ago Changed 03a5e315bdad
- 19d ago First seen · 168 lines · 90 tokens per session scan A b515a2f85d65
cosim-gpu-info-gathering is a skill published in the GitHub repository gevico/cosim-gpu (95 stars, last pushed 4d ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,708 once invoked, about $0.0004 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 2026-10-10.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…