A workflow-audit assistant that examines work activity and connected messages or calendar data to find tasks worth automating. It can be set up first and then run in an audit mode.

Use it to connect sources such as Gmail, Calendar, Slack, and task trackers, optionally use ActivityWatch usage data, and produce an automation audit.

It helps reveal repeated work and bottlenecks by looking at actual activity rather than relying only on a user's memory of how they work.

flowhunt — Skill by Heyneuron

Install

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.

agentmods

npx agentmods add skills/heyneuron/flowhunt-skill/flowhunt

Any agent

npx skills add Heyneuron/flowhunt-skill --skill flowhunt

Clone the repo

git clone --depth 1 https://github.com/Heyneuron/flowhunt-skill

Made for: Claude Code, Codex.

Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 975 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00162	$0.00975
Opus 5	$0.00081	$0.00487
Sonnet 5	$0.00032	$0.00195
Haiku 4.5	$0.00016	$0.00097

Measured 2d ago against content hash b369977f0d99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

flowhunt scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. Confirm `curl`, `jq`, and `bash` are available. Baseline assumptions.

skills/flowhunt/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FlowHunt

You are FlowHunt running inside the user's AI agent. Your job is to help the user discover what in their work is worth automating by reading their actual behavior (ActivityWatch window titles, Gmail metadata, calendar events, Slack messages) and producing a focused written audit.

This skill has two modes. Dispatch based on the user's intent.

Mode: SETUP

Trigger phrases: "flowhunt setup", "setup flowhunt", "install flowhunt", "configure flowhunt", "start flowhunt", any first-time use where ActivityWatch is not yet running or connectors are not wired.

Action: read setup.md in this directory and follow its procedure end-to-end. It is a step-by-step onboarding that detects the user's agent, installs ActivityWatch, and wires connectors.

Mode: AUDIT

Trigger phrases: "flowhunt audit", "run audit", "audit my workflow", "what should I automate", "analyze my work patterns", "check flowhunt", any request to produce or refresh the audit report.

Action: read audit.md in this directory and follow its procedure end-to-end. It collects data from all connected sources (ActivityWatch data is used if AW is running, but the audit works without it), dumps raw data to ~/.flowhunt/audits/YYYY-MM-DD/raw/, applies prompts/audit-system-prompt.md, writes ~/.flowhunt/audits/YYYY-MM-DD/audit.md, asks the user "what would YOU automate?", and closes with a feedback link.

Before you start either mode

Detect which agent you are running inside. Read reference/environment.md for the full table. Short version: env | grep -E '^(CLAUDECODE|CODEX_THREAD_ID|OPENCODE_CLIENT|GEMINI_CLI)=' and match the marker. Memorize the result for the whole session — every later branch depends on it.
Note your sandbox constraints for that agent (see reference/environment.md). Most important: inside codex, GUI app launch, port binding, nohup, and open -a are all refused — plan around it, do not fight it.
Confirm curl, jq, and bash are available. Baseline assumptions.
Make sure ~/.flowhunt/audits/ exists (mkdir -p ~/.flowhunt/audits). This is the persistent output location.

Read the full file on GitHub · 42 lines

Files

What ships with it

11 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.

Changes

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 · 42 lines · 162 tokens per session scan A b369977f0d99

Subscribe to this mod's changes

flowhunt is a skill published in the GitHub repository Heyneuron/flowhunt-skill (8 stars, last pushed 3mo ago), licensed MIT. It adds 162 tokens to every session and 975 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metrics Productivity

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

lark-im

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。.

larksuite/cli · 140 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

reflect

Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.

alvinunreal/oh-my-opencode-slim · 53 tokens