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 skills add dromologue/workflowyMCP --skill wflowgit clone --depth 1 https://github.com/dromologue/workflowyMCPWrote 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/dromologue/workflowymcp/wflow)<a href="https://agentmods.dev/skills/dromologue/workflowymcp/wflow"><img src="https://agentmods.dev/badge/skills/dromologue/workflowymcp/wflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dromologue/workflowymcp/wflow"><img src="https://agentmods.dev/badge/skills/dromologue/workflowymcp/wflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 134 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 361 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Agent Snooping · line 391 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 784 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 786 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00000 | $0.25584 |
| Opus 5.5 | $0.00000 | $0.10234 |
| Sonnet 5.5 | $0.00000 | $0.05117 |
| Haiku 4.5 | $0.00000 | $0.02558 |
Grade A, and why
wflow 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 1mo 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 — 850 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wflow — second-brain skill (template)
This is the generic skill template shipped by the workflowy-mcp-server repo. It deliberately contains no user-specific node IDs — those live in $SECONDBRAIN_DIR/memory/workflowy_node_links.md. On first use, walk the user through populating that file (see Bootstrap below).
Read the next section before anything else. Most of this file is operating detail: hazards, contracts, failure modes, tool routing. That detail exists to serve one method, and a session that executes the plumbing correctly while breaking the method has failed. The method is short; the plumbing is long because it was expensive to learn, not because it matters more.
The skill spans the full second-brain loop:
- Capture — tasks, links, ink, reading material.
- Triage and prioritisation — daily / weekly / monthly cascade.
- Synthesis — distillation of reading and conversation into atomic notes.
- Retrieval — graph queries across Workflowy and any additional services the user has configured.
It is invoked conversationally — the user does not need to type slash commands. Match by intent, not by exact wording.
Which surface am I on
Up to four MCP surfaces can reach the same Workflowy account: this server over stdio on the user's machine (mcp__workflowy__*), the WorkFlowy CLI (mcp__workflowy-cli__*, if wf is installed and wired in), WorkFlowy's own desktop MCP inside the desktop app (mcp__workflowy-desktop__*), and — if the user has deployed one — a remote connector for claude.ai web/mobile and cloud sandboxes, which is this same server behind an HTTP shim. Decide by device first, then by capability.
Decide in one line. On the user's machine, route reads, searches and ordinary writes to a native surface (the CLI, or the desktop MCP when the app is running) and come to this server for method work — mirror discipline,
review, anything touching$SECONDBRAIN_DIR, anything scheduled. Never use a remote connector from a machine that can reach this server: they share one Workflowy account and therefore one API rate limit, so local traffic routed remotely burns the quota the mobile and cloud surfaces depend on. If a native surface is unavailable, fall back to this server automatically; never fall outward to the connector.
What ships with it
1 file 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.
- 1mo ago Changed 0de8048e0b91
- 1mo ago Changed · +51 lines 4af94416beb1
- 1mo ago Changed · +12 lines adaa129743df
- 1mo ago Changed · +31 lines · -95 tokens per session c0d14ae6f4b8
- 1mo ago First seen · 756 lines · 95 tokens per session scan A 4f6898605b50
wflow is a skill published in the GitHub repository dromologue/workflowyMCP (11 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 25,584 tokens. 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 2026-08-31.
Other skills, from other repositories
memora
Use when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.
cortex-profile
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…
any-mcp
Use when an agent needs to read, search, create, edit, organize, upload, or chat with Anytype through the bounded any-mcp server. Covers safe tool selection, exact identifier chaining, optional toolsets, common PKM workflows, and the narrow anyr fallbacks for chat subscriptions and rich chat blocks.
obsidian-web-mcp
Set up or maintain an Obsidian vault with a desktop ChatGPT web sidebar community plugin and a vault-scoped MCP server exposed through ngrok. Use when asked to configure Obsidian plugins, install or update a ChatGPT web sidebar, expose an Obsidian vault to ChatGPT/MCP, add read/write vault tools, add Agent…
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
session-context-ops
Canonical session, context, onboarding, compaction, and token-budget operations for preserving and managing agent work across sessions.