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 flagos-ai/skills --skill flaggems-pr-submit-flagosgit clone --depth 1 https://github.com/flagos-ai/skillsWrote 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/flagos-ai/skills/flaggems-pr-submit-flagos)<a href="https://agentmods.dev/skills/flagos-ai/skills/flaggems-pr-submit-flagos"><img src="https://agentmods.dev/badge/skills/flagos-ai/skills/flaggems-pr-submit-flagos/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/flagos-ai/skills/flaggems-pr-submit-flagos"><img src="https://agentmods.dev/badge/skills/flagos-ai/skills/flaggems-pr-submit-flagos.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 | $0.00100 | $0.02829 |
| Opus 5 | $0.00050 | $0.01414 |
| Sonnet 5 | $0.00020 | $0.00566 |
| Haiku 4.5 | $0.00010 | $0.00283 |
Grade A, and why
flaggems-pr-submit-flagos 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 10d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FlagGems 算子 PR 提交 Skill
提交流程：规范名查询 → 建分支 → 提取 worktree 代码(6文件) → 脚本验证 → pre-commit → push → 创建 PR → 回填链接。
Rules（违反会导致 PR 被拒）
25+ 项检查已由
check_operator.py自动执行（详见下方检查表），以下仅列出模型需主动注意的规则。
流程规则
- 先跑脚本再 commit —
check_operator.py --strict必须 0 errors - 使用规范命名 — 提交前用
operator_registry.py lookup查询 - 回填 PR 链接 — PR 创建后必须
operator_registry.py backfill - PR 描述由脚本生成 —
gen_pr_description.py输出 JSON，映射到模板（英文）
代码规则
- 代码必须与 worktree 原版一致 — 不允许重写测试逻辑，仅允许 import 调整和格式化
- 不删 worktree 现有注释
- 下划线命名 — 前导
_的算子，mark/yaml id/文件名去掉下划线，其余保留（详见references/naming.md） - dtype 默认用常量 — test 用
utils.FLOAT_DTYPES，benchmark 用consts.FLOAT_DTYPES；CUDA 不支持时可硬编码但必须加注释 - 非 pointwise benchmark — 简单场景用
GenericBenchmark(input_fn=...)；需要自定义 shape 时继承并覆盖set_shapes - hardcode size 需加注释 — kernel BLOCK、test shapes、benchmark shapes 都需注释说明原因
- 不支持的 dtype 在 wrapper 加 assert
- overloaded ops yaml 拆成独立条目 — 参考
eq/eq_scalar模式 - 禁止 .is_cuda — 设备判断使用
flag_gems.device，不用.is_cuda或device.type == "cuda"（多后端） - Autotune 配置放 config 文件 — 不在 kernel 中内联硬编码 autotune configs
- Logger 格式 —
logger.debug("GEMS <OP_NAME_UPPER>")，不用其他格式 - Fused 算子放 fused/ 目录 —
src/flag_gems/fused/，不放src/flag_gems/ops/
提交规则
- 不修改上游已有测试 — 只新增，不改已有函数
- 先提交通用版，再提交特化版
- 概率算子用统计验证 — mean ≈ p，不能只查 0/1
- nan 比较用 gems_assert_close(equal_nan=True)
What ships with it
14 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.
- LICENSE.txt 11 KB
- README.md 5.7 KB
- references/common-issues.md 8.5 KB
- references/naming.md 2.4 KB
- references/pr-checklist.md 4.1 KB
- references/pr-template.md 3.4 KB
- references/workflow.md 5.8 KB
- scripts/check_operator.py 60 KB runs code
- scripts/check_overload_consistency.py 10 KB runs code
- scripts/extract_from_worktree.py 33 KB runs code
- scripts/gen_pr_description.py 19 KB runs code
- scripts/operator_registry.py 7.6 KB runs code
- scripts/pr_gate_check.sh 1.9 KB runs code
- scripts/submit_operator.py 17 KB runs code
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.
- 10d ago First seen · 185 lines · 100 tokens per session scan A 4aeccf448c9c
flaggems-pr-submit-flagos is a skill published in the GitHub repository flagos-ai/skills (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 2,829 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
pr-pending-feedback
Evaluate pending (unsubmitted) review comments on the current branch's PR and, after user confirmation, address each in a separate sub-agent and separate commit.