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-harnessnpx skills add WackyGem/Fleur --skill fleur-harnessgit clone --depth 1 https://github.com/WackyGem/FleurWrote 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/wackygem/fleur/fleur-harness)<a href="https://agentmods.dev/skills/wackygem/fleur/fleur-harness"><img src="https://agentmods.dev/badge/skills/wackygem/fleur/fleur-harness.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.02593 |
| Opus 5 | $0.00048 | $0.01296 |
| Sonnet 5 | $0.00019 | $0.00519 |
| Haiku 4.5 | $0.00010 | $0.00259 |
Grade A, and why
fleur-harness 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 6d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleur Harness
当任务不只是改一段代码,而是要提升 fleur 的可维护性、agent 可读性、架构约束或长期执行可靠性时,使用这个 skill。
核心原则:AGENTS.md 是仓库入口地图,docs/architecture/ 是当前项目状态、代码根、职责边界和架构事实入口,docs/ 是记录系统,测试和脚本是可执行约束。不要把长期规则只留在一次性提示或聊天上下文里。
适用场景
- 复杂重构、跨模块改动、架构边界调整。
- 新增数据源、Dagster asset、dbt 模型、迁移或长期运行任务。
- 维护
AGENTS.md、ADR、RFC、plan、optimize 文档、job report 或 repo skill。 - 把重复出现的问题沉淀为测试、脚本、文档规则或专用 skill。
- 检查文档是否过期、重复、互相冲突或没有对应机械验证。
工作循环
- 先读地图:从
AGENTS.md、docs/README.md和相关docs/architecture/入口确认项目结构、命令、边界和质量门禁。 - 再分流落点:根据需求影响范围决定进入 RFC、plan、ADR、jobs、references、design、archive 或直接修改。
- 再读事实:用
rg/find查真实代码、测试、现有文档和最近报告,不用旧文档替代当前代码。 - 明确意图:小变更可直接执行;复杂方案写
docs/RFC/,跨阶段实施写docs/plans/,长期约束写docs/ADR/。 - 编码约束:反复出现的 review 意见或架构偏好,优先沉淀为测试、脚本、skill 或 AGENTS/docs 路由。
- 验证闭环:按改动范围运行最小可证明的检查,并在文档中记录无法验证的原因。
- 清理熵增:发现过期文档、废弃计划、重复规则或源码噪声时,随任务一并收敛,避免继续复制坏模式。
文档路由
docs/README.md:docs 总入口,提供按当前架构查事实和按文档类型追溯的入口。docs/architecture/:当前项目状态、代码根、职责边界、运行入口、质量门禁、架构边界和 dbt layer 模型语义;新增长期系统、应用、服务或子域时同步维护。AGENTS.md:repo 入口地图,只放稳定目录、命令、边界和 skill 路由;不要扩展成百科。docs/ADR/:已经接受的长期决策;当行为应长期稳定且影响后续设计时新增或更新。docs/RFC/:方案讨论和历史设计;实现完成或废弃后移动到archive/或在文档中标明状态。docs/plans/:复杂执行计划、阶段拆分、验收标准;活跃计划保留在顶层,完成后归档;新增、归档或改名 active plan 后同步维护docs/plans/README.md。docs/issues/:技术债、实现漂移、质量扫描、维护性审计和治理建议入口。docs/jobs/reports/:实际运行、回填、重跑和数据核验记录;必须包含命令、时间、范围和结果。docs/architecture/dbt_layer/:dbt layer 和模型设计文档,记录模型语义、字段边界和对应 SQL/YAML。docs/references/:远端接口、OpenAPI、数据字典、样例图片、服务器协议等可查事实。docs/skills/:可复用 agent 操作手册;只保留SKILL.md和必要 references/scripts/assets。
架构事实文档写法
docs/architecture/*.md 是当前事实入口,不是新的一套 RFC 或 README 复制品。架构事实文档应保持短而可导航,优先包含:
- 状态和代码根。
- 职责、非职责和主要依赖。
- 运行入口和最小质量门禁。
- 相关当前文档、ADR、RFC、plan、job report、reference 和 skill 指针。
- 待决问题。
架构事实文档不应承载长篇设计、完整 API 规格、字段字典、执行计划或运行报告;这些内容留在对应生命周期目录中,再由架构事实文档链接。
文档地图阅读顺序
处理 harness、架构、长期维护或文档治理任务时,按下面顺序读文档;只在任务相关时深入,不要无差别通读整个 docs/。
AGENTS.md:确认项目入口、命令约束、质量门禁、MCP 路由和 skill 路由。docs/README.md:确认 docs 当前架构事实入口、文档类型入口、目录职责、状态模型和归档规则。docs/architecture/README.md和docs/architecture/project-status.md,再读相关docs/architecture/*.md:确认当前代码根、职责边界、运行入口、质量门禁和相关文档指针。docs/architecture/中与该子域相关的当前架构文档:确认跨模块边界、依赖方向和禁止模式。docs/ADR/README.md,再读相关docs/ADR/*.md:确认已经接受且仍应遵守的长期决策。- 活跃设计与执行文档:先读相关
docs/RFC/*.md,再读相关docs/plans/*.md,确认目标、非目标、阶段和验收标准。 - 运行事实:涉及回填、重跑、数据核验、性能或生产结果时,读
docs/jobs/README.md、docs/jobs/dagster-backfill-2026.md和相关docs/jobs/reports/*.md。 - 接口与数据事实:涉及远端 API、schema、样例、数据契约或字典时,读相关
docs/references/README.md、docs/references/openapi/、docs/references/remote_endpoint/、docs/references/data_dict/、docs/references/remote_server/。 - 复用手册:涉及具体 agent 操作时,读相关
docs/skills/*/SKILL.md,并遵守其中更具体的 runbook。 - 历史材料:
docs/RFC/archive/、docs/plans/archive/和docs/issues/只用于追溯背景;不得把归档内容当作当前事实,除非架构事实文档、当前代码或活跃文档再次确认。
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.
- 6d ago First seen · 142 lines · 97 tokens per session scan A a165beb5debc
fleur-harness is a skill published in the GitHub repository WackyGem/Fleur (114 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 2,593 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…