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 agentmods add skills/wackygem/fleur/fleur-worktreenpx skills add WackyGem/Fleur --skill fleur-worktreegit clone --depth 1 https://github.com/WackyGem/FleurWhat 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 | $0.00074 | $0.02507 |
| Opus 5 | $0.00037 | $0.01254 |
| Sonnet 5 | $0.00015 | $0.00501 |
| Haiku 4.5 | $0.00007 | $0.00251 |
Grade C, and why
fleur-worktree scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **直接 `rm -rf` 会留下 stale metadata**：优先 `git worktree remove`，必要时再 `git worktree prune`。 How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleur Worktree
当同一个 fleur 仓库需要同时推进多个 Codex/agent 任务时，使用这个 skill。目标是一任务一 worktree、一任务一分支、一套明确验证和清理规则，避免 agent 互相踩文件、共享运行时状态或把未完成分支混入主工作区。
依据
- OpenAI Codex app 公开材料强调并行 agent、内置 worktrees、隔离环境和可审阅 diff。
- OpenAI harness engineering 文章提到让应用可按每个 Git worktree 启动，使 Codex 能为每个变更管理独立实例。
- Git 官方
git-worktree文档定义了add、list、remove、prune等生命周期命令；清理 worktree 时优先用 Git 命令而不是直接删除目录。
原则
- 每个并行任务使用独立 worktree 和独立 branch。
- worktree 放在仓库外部的兄弟目录，不放进
fleur/内部。 - 不从脏工作区创建新任务，除非用户明确要求把当前未提交改动带过去。
- worktree 只隔离文件系统和 Git checkout，不隔离 S3、PostgreSQL、Dagster run storage、端口、后台进程或外部 API。
- 能串行就不伪装并行：两个任务会改同一模块、同一迁移、同一资产契约或同一运行状态时，指定 integrator 分支串行合并。
- 合并前必须在目标分支上重新验证；合并后必须清理 worktree 和 stale metadata。
布局
主仓库：
/storage/program/fleur
推荐 worktree 根目录：
/storage/program/fleur-worktrees/
命名规则：
- worktree 目录：
<yyyymmdd>-<short-task> - branch：
codex/<yyyymmdd>-<short-task> - slug 只用小写字母、数字和
-。
示例：
/storage/program/fleur-worktrees/20260531-scheduler-runner
branch: codex/20260531-scheduler-runner
创建流程
在主仓库或任意干净 worktree 中执行：
git status --short
git worktree list
git fetch --all --prune
mkdir -p ../fleur-worktrees
git worktree add -b codex/20260531-topic ../fleur-worktrees/20260531-topic HEAD
如果要基于远端主线创建，先确认默认分支名，再显式指定：
git branch --show-current
git worktree add -b codex/20260531-topic ../fleur-worktrees/20260531-topic origin/main
进入新 worktree 后先同步依赖：
cd ../fleur-worktrees/20260531-topic/pipeline
uv sync --all-packages --all-groups
环境隔离
.env 不提交。需要运行本地命令时，按任务选择：
- 只做文档、静态代码、单测：通常不需要复制
.env。 - 需要访问同一套外部 S3/PostgreSQL/API：可以复制或软链接
.env，但必须确认任务不会写入生产或共享状态。 - 需要并行运行 Dagster、服务或数据库相关任务：不要共享
DAGSTER_HOME、端口、临时目录或本地数据库 schema。
Dagster 运行建议：
dg check defs、ruff、pyright、pytest 可在 feature worktree 内运行。- 物化、回填、OCR、外部 API 写入类任务默认不要从普通 feature worktree 执行。
- 如果确实要在 worktree 中运行 Dagster，使用该 worktree 自己的
.dagster，并在命令前显式设置DAGSTER_HOME="$PWD/.dagster"。 - 任何涉及真实 S3/PostgreSQL 写入的操作，先使用
docs/skills/fleur-dagster-backfill-runbook/SKILL.md判断是否应该切回主工作区或专用 ops worktree。
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.
- 3d ago First seen · 255 lines · 74 tokens per session scan C 98225776a764
fleur-worktree is a skill published in the GitHub repository WackyGem/Fleur (110 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 2,507 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…