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/xaiht/tlamatini/flow_makingnpx skills add XAIHT/Tlamatini --skill flow_makinggit clone --depth 1 https://github.com/XAIHT/TlamatiniWrote 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/xaiht/tlamatini/flow_making)<a href="https://agentmods.dev/skills/xaiht/tlamatini/flow_making"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/flow_making.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 | $0.00038 | $0.01731 |
| Opus 5 | $0.00019 | $0.00865 |
| Sonnet 5 | $0.00008 | $0.00346 |
| Haiku 4.5 | $0.00004 | $0.00173 |
Grade A, and why
flow-making 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 5d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow-Making
Related (2026-07-22): FlowCreator is now ALSO a plain wrapped chat-agent,
chat_agent_flowcreator— a Multi-Turn tool (no ACPX needed) that takesprompt=+flow_filename=and writes the.flwitself. This skill is the heavier, ACPX/invoke_skill-surface path that shells out toscripts/make_flow.py; the wrapped tool is the lighter one-call path. Both convertflow_result.json→.flwwith the SAMEresult_to_flw.pylogic — this skill'sscripts/result_to_flw.pyand the copy vendored atagent/agents/flowcreator/result_to_flw.py(so the pool subprocess can carry it) must be kept in sync. For a simple "make me a .flw from this sentence" ask, preferchat_agent_flowcreator; use this skill when you need the scripted pipeline.
Produce a canvas-loadable .flw from ${input.objective} by wrapping the
FlowCreator engine — which already encodes the full 83-agent catalog,
connection contracts, and design rules in agentic_skill.md. Do NOT hand-author
the .flw JSON yourself: you do not carry the agent catalog/config-key contracts
in context, so a hand-written flow hallucinates agent types and will not load.
Primary path — one deterministic call
Run the shipped driver with execute_command. It copies the FlowCreator
template to an isolated runtime dir, writes its config.yaml, runs FlowCreator
(which queries the configured Ollama model), and converts the result to a .flw:
python agent/skills_pkg/flow_making/scripts/make_flow.py \
--objective "${input.objective}" \
--out "${input.out_path}" \
--flow-name "${input.flow_name}" \
--model "${input.llm_model}" \
--host "${input.llm_host}"
What ships with it
3 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.
- 5d ago First seen · 139 lines · 38 tokens per session scan A 407c5f7e860a
flow-making is a skill published in the GitHub repository XAIHT/Tlamatini (16 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,731 once invoked, about $0.0002 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
release
Release a new version of the project.
commit
Inspect git status, draft a commit message that matches the repo's style, and commit staged changes.
review
Review current code changes for bugs, regressions, test gaps, and project-guideline violations.
trend-analysis
基于多维度数据进行分级评估与趋势预测，通过设定差异化增长率计算预测值，并生成对比可视化图表，适用于绩效评估、目标设定等场景。.
excel-basic-statistics-and-routing
Skill "excel-basic-statistics-and-routing" from OpenSenseNova/SenseNova-Skills, covering skill steps, 保存区间提取与汇总结果 and 保存筛选与统计结果.
dynamic-percentage-and-large-file-analysis
根据文件行数动态切换大文件处理策略（Parquet转换），通过逐行扫描或列匹配提取关键指标并计算占比、均值等统计量，最终输出结构化Excel报告及可视化图表。.