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/remon-16/flow-forge/flowforge-testingnpx skills add Remon-16/flow-forge --skill flowforge-testinggit clone --depth 1 https://github.com/Remon-16/flow-forgeWhat 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 | $0.00090 | $0.02867 |
| Opus 5 | $0.00045 | $0.01434 |
| Sonnet 5 | $0.00018 | $0.00573 |
| Haiku 4.5 | $0.00009 | $0.00287 |
Grade A, and why
flowforge-testing 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 2d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow Forge Test Case Generation & Execution
1. Preflight
- Locate the flow-forge repository root: prefer
flowforge_rootfromflowforge.config.yaml; otherwise use the parent directory of this skill. Verify thepython/andshared/layout exists. - Load
flowforge.config.yaml. If it does not exist, copy it fromflowforge.config.yaml.exampleand ask the user for the key settings (language, Python environment, executor defaults). - Resolve the Python interpreter by running
scripts/resolve_python.py. Resolution order:python_path(explicit) -> configured mode (conda/venv/system) -> automatic detection. The chosen interpreter must be able to importrequests,openpyxlandyaml. - If dependencies are missing, ask the user to install them in the
configured environment (for example
conda activate api_test && pip install -r python/requirements.txt). Never install packages into the conda base environment. - Check the executor configuration (
python/env.ymlandpython/env-{envName}.yml). Fill in missing appbaseURL, login settings andprocessor_configsentries from the user's deployment notes or documentation. If credentials are still missing, ask the user once for them; never guess or fabricate credentials. - Prepare middleware when needed: run
python/tools/h2/init_h2.pyfor H2; start the system-under-test or middleware services as background subprocesses and record their PIDs so the main flow never blocks. If a service cannot be started automatically, report it to the user.
2. Inputs
- Requirement documents:
.md/.txt/.pdf, one or more. Analyze each document separately, then merge and deduplicate by content (business flows, roles, constraints, exceptions). - API documents: OpenAPI 3.0 (
JSON/YAML) or Markdown tables, one or more. Merge and deduplicate interfaces by(path, method). - Optional supplementary inputs: table structures/DDL, business rules, existing test cases, middleware connection information, deployment notes. Use them during requirement analysis and case generation; do not output them as separate artifacts.
What ships with it
15 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.
- flowforge.config.yaml.example 1.3 KB
- README.en.md 4.1 KB
- README.md 4.0 KB
- references/PLAN_TEMPLATE.md 2.9 KB
- scripts/ff_tool.py 24 KB runs code
- scripts/i18n/__init__.py 213 B runs code
- scripts/i18n/en_US.json 1.9 KB
- scripts/i18n/loader.py 1.8 KB runs code
- scripts/i18n/zh_CN.json 1.8 KB
- scripts/resolve_python.py 7.5 KB runs code
- scripts/tests/__init__.py 45 B runs code
- scripts/tests/conftest.py 390 B runs code
- scripts/tests/test_ff_tool.py 3.9 KB runs code
- scripts/tests/test_resolve_python.py 3.6 KB runs code
- scripts/tests/test_validate_cases.py 8.9 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.
- 2d ago First seen · 261 lines · 90 tokens per session scan A 3db64ba634d2
flowforge-testing is a skill published in the GitHub repository Remon-16/flow-forge (11 stars, last pushed 26d ago), licensed MIT. It adds 90 tokens to every session and 2,867 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
API Test Suite Generator
Automatically generate comprehensive API test suites from OpenAPI specifications covering CRUD operations, error handling, authentication, pagination, and edge cases.
api-test-E10
当前 test-automation 项目内置的接口自动化编写 skill,物理位置 .claude/skills/api-test-E10/。用于在 \test-automation\E10自动化\接口自动化测试 中新增、维护、补齐、迁移接口测试方法与 pytest 用例。触发场景包括:新增接口方法、新增接口测试用例、参考 Java Controller 源码或 Jacoco 报告补齐未覆盖接口、维护已有接口方法与用例、补齐参数化、修复接口断言、按指定位置插入代码、按 URL 查重复实现、处理 UTF-8 中文编码、执行 pytest 并根据真实报错循环修复直到通过。运行时产物统一放在项目根 apitestdwptemp/…
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
analyze-market
Perform a market analysis for a product category or segment. Trigger on: market analysis, market size, TAM SAM SOM, market opportunity, industry analysis.