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-review/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-review)<a href="https://agentmods.dev/skills/gevico/cosim-gpu/cosim-gpu-review"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-review/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-review"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-review.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 | $0.00045 | $0.00767 |
| Opus 5.5 | $0.00018 | $0.00307 |
| Sonnet 5.5 | $0.00009 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
cosim-gpu-review 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 19d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cosim Review
Review local cosim changes through an independent reviewer workflow. This skill
owns review orchestration, finding disposition, and PR-ready evidence. Shared
reviewer isolation, prompt hygiene, source-base, build, and formatting rules
live in references/review/independent-review-contract.md; read that file
before delegation or maintainer audit.
Entry Rules
- Start from a
cosim-gpu-flow-plan --type reviewplan whose Confirmed Target section is complete. - Exception: if the user explicitly supplies a standalone review brief, inspect only the files and artifacts permitted by that brief, do not modify source, and return findings ordered by severity.
- Map older names such as
cosim-reviewto this skill. - The user controls round count and stopping rule when they supply them. Default: one independent review round, followed by maintainer audit.
- When invoked from
cosim-gpu-rlcr-loop, follow the RLCR stop rule instead of asking after each clean round.
Ask only before widening reviewed scope, changing base reference, changing target programs or fixed environment rows, using a nonstandard binary, requesting a full or cold rebuild, editing a disk image, deleting files outside repository cleanup scripts, accessing external services, or creating a pull request.
Workflow
- Read
references/review/independent-review-contract.md. - Read optional domain references when relevant:
references/review/gem5-format-hygiene.mdfor gem5 formatter scope, commit splitting, or style churn.references/review/github-actions-ci.mdfor GitHub Actions YAML.
- Write
artifacts/<slug>/reviews/review-round-N-brief.mdfromplan.md, scoped diffs, test evidence, and public review comments. - Send the brief to an independent reviewer through
cosim-gpu-codex-review. - Save output as
artifacts/<slug>/reviews/review-round-N-adversarial.md. - Audit every finding and save
artifacts/<slug>/reviews/review-round-N-audit.md. - Update
artifacts/<slug>/review-findings.mdwith accepted, rejected, fixed, or deferred status. - After accepted source or behavior changes, run the standard incremental
build and affected test rows through
cosim-gpu-buildandcosim-gpu-test.
What ships with it
3 files 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.
- 19d ago First seen · 73 lines · 45 tokens per session scan A 4cbf2c9d5767
cosim-gpu-review is a skill published in the GitHub repository gevico/cosim-gpu (95 stars, last pushed 4d ago), licensed Apache-2.0. It adds 45 tokens to every session and 767 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 2026-10-10.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…