Publish Sign in

Agent modes

Guidelines to create/update a new mode for PostHog AI agent.

You say
Install this skill Read the source first Free Written by PostHog · unverified publisher
Context cost
1.2k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 4.7 kBtext throughout, nothing executable
Licence
MITfree to use
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what conditions. Achieve better results using your plan mode.

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Workflow

Runs a procedure end to end.

analyticsagent
Filed under

Analytics & Monitoring

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md4.7 kB · 82 lines
--- name: implementing-agent-modes description: Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what conditions. Achieve better results using your plan mode. ---
6# Agent modes
7
8Use the steps below to plan or implement a new mode. A mode is a way to manage the context of the agent and inject tools, prompts, and mode-related behavior relevant to a product, use case, JTBD, etc. The agent has the switch_mode tool that allows it to switch itself to another mode, which might change tools, prompt, and executables, preserving the current context. Some previously created tools are contextual, meaning they're injected on particular pages of the frontend. The modes change the approach and always have tools in the mode context.
9
10## Determine mode name
11
12Explore the ee/hogai/core/agent_modes/presets directory and check if there are already modes that match the user's intent. If you want to create a new mode, you should scope it by a PostHog product (Product analytics), product area (SQL), or agent (Instrumentation agent).
13
14## (optionally) Create a new mode in schema
15
16Add a new AgentMode to frontend/src/queries/schema/schema-assistant-messages.ts and regenerate the schema using:
17
18```bash
19hogli build:schema
20```
21
22Alternatively, you may use this command:
23
24```bash
25pnpm run schema:build
26```
27
28## Create or update mode's scaffolding
29
30A mode should typically contain at least two things:
31
32- An AgentToolkit exposing tools that are specific to the mode and trajectory examples for the todo tool.
33- An AgentModeDefinition containing the AgentMode, mode description that is always injected into the context window of the agent, and classes for toolkit and executables.
34
35Note: you should only create new executables if the user needs to modify the prompt, behavior of that mode, or the execution loop itself.
36
37## Adding tools to the mode
38
39Relevant tools might be located in ee/hogai/tools or products/<product_name>/backend/max_tools. There is a set of tools that is always injected into the context, like the read_data tool, but all other tools should be specific to the mode.
40
41Before adding a tool to the toolkit, determine if those tools have tool dependencies. If there are dependencies (like an experiment depends on feature flag creation), loop back to the user to determine whether they want to merge modes into a single one. If they don't want to do that, make sure that you later add a trajectory example clearly explaining mode switching and tool selection.
42
43You should also verify that the tools are backend-first. If tools apply frontend changes without passing proper context back to the conversation, you should propose a way to make them backend-first so the agent has the right context.
44
45## Review the default toolkit
46
47If the new mode contains new Django models, you should review whether the read_data, search, and list_data tools have the functionality to retrieve the models. If they don't support these models, you should use or implement one of the context providers available in ee/hogai/context/....
48
49## Write JTBD-like trajectory examples
50
51Update the AgentToolkit to include trajectory examples. These should be JTBD-style examples showing how the agent should achieve typical tasks with the available tools. Check the Product analytics preset for reference.
52
53## Implement frontend
54
55Update max-constants.tsx to include new tools and add the mode to the mode selector. You might also need to create new UI elements for displaying data from the tools.
56
57### Example
58
59Say you've updated the Error tracking tool to list issues. It used to be a frontend tool that only updated filters, but now it outputs error tracking issues. While the agent has the context it needs, the user also needs to see the issues in a human-readable way. In this case, you should design and implement a new component to display the tool's output.
60
61## Add feature flag
62
63All new modes must be feature-flagged. Example:
64
65```ee/hogai/chat_agent/mode_manager.py
66 @property
67 def mode_registry(self) -> dict[AgentMode, AgentModeDefinition]:
68 registry = dict(DEFAULT_CHAT_AGENT_MODE_REGISTRY)
69 if has_error_tracking_mode_feature_flag(self._team, self._user):
70 registry[AgentMode.ERROR_TRACKING] = error_tracking_agent
71 return registry
72```
73
74If you have created new tools, make sure you feature flag them correctly:
75
761. Old tools that are being migrated should not be available if the feature flag is active.
772. New tools should only be available if the feature flag is active.
78
79## Implement and update tests
80
81You should test new tools, presets, executables, and optionally implement evals.
82
In the file
SKILL.md714 words
Files1
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈70
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,105
on trigger
The instruction body, read only when the skill fires.
0.59%
of a 200k window
Ten skills this size would take about 6% of the window before you open a file.
050k100k150k200k context window

1.2k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Small enough to keep loaded permanently without thinking about it.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption
Installsnone yet
Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for
Writes filesno
Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 4.7 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md4.7 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Agent modes · 1.2k tokens when loaded npx mcprush@latest skill add posthog/agent-modes

Writes to .claude/skills/agent-modes/ in the current project. Add --global to put it in your home directory instead, for every project.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/
Claude Desktop
ChatGPT
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok.grok/skills/
Zed.agents/skills/
Windsurf.windsurf/skills/
Agent SDK.claude/skills/
HTTP / API
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceposthog/agent-modes

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v
  • No earlier releases have been published to the marketplace.
Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

PO
PostHog

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill