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-flow-plan/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-flow-plan)<a href="https://agentmods.dev/skills/gevico/cosim-gpu/cosim-gpu-flow-plan"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-flow-plan/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-flow-plan"><img src="https://agentmods.dev/badge/skills/gevico/cosim-gpu/cosim-gpu-flow-plan.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 | $0.00054 | $0.01173 |
| Opus 5.5 | $0.00022 | $0.00469 |
| Sonnet 5.5 | $0.00011 | $0.00235 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
cosim-gpu-flow-plan 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cosim Flow Plan
Use as the first step for non-trivial cosim tasks: testing, bug localization, code review, or iterative implementation. It creates a standardized task workspace and hands off to the domain skill.
Do not use this skill for ordinary repository maintenance: commit splitting,
submodule pointer updates, history rewriting requested only for commit hygiene,
author configuration, .gitignore changes, documentation-only cleanup, or
skill-directory refactoring that does not require cosim execution evidence.
Hard policy
- For cosim test, debug, review, and RLCR tasks, do not modify source files before the plan is written and the evidence ledger has confirmed the target.
- Review tasks require explicit human confirmation of the target before any reviewer delegation, test execution, or source edit. The confirmed target must name the reviewed change, base reference, file or subsystem scope, allowed source changes, required evidence, and stopping rule if one is supplied.
- All agent-created artifacts stay under
artifacts/<task-slug>/. - Do not add AI roles such as Codex or Claude to contribution trailers. When a commit needs
Signed-off-by, use the human author identity fromgit config user.nameandgit config user.email. - Formatting must be diff-scoped. Whole-file or project-wide formatter output
mixed with behavior changes is a hard failure unless the confirmed task is
explicitly formatting-only. Prefer
clang-format-diff, gem5's modified-range style tools, or an equivalent patch-range formatter; otherwise format only the changed hunk and its immediate context. Before commit, compare normal diff stats with whitespace-ignored diff stats and remove unrelated formatter churn. - Optimization edits must be based on current
HEAD. A historical commit may be the reviewed change, but source changes are applied to checked-outHEADafter recordinggit rev-parse HEADand whether the reviewed commit is an ancestor ofHEAD. If later commits already changed the same area, classify findings against currentHEADbefore editing.
What ships with it
2 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 · 144 lines · 54 tokens per session scan A 3844e7128316
cosim-gpu-flow-plan is a skill published in the GitHub repository gevico/cosim-gpu (95 stars, last pushed 4d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,173 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.