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 agents/posthog/posthog-foss/activity-log-expertgit clone --depth 1 https://github.com/PostHog/posthog-fossWrote 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/agents/posthog/posthog-foss/activity-log-expert)<a href="https://agentmods.dev/agents/posthog/posthog-foss/activity-log-expert"><img src="https://agentmods.dev/badge/agents/posthog/posthog-foss/activity-log-expert.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 | $0.00165 | $0.00467 |
| Opus 5 | $0.00082 | $0.00234 |
| Sonnet 5 | $0.00033 | $0.00093 |
| Haiku 4.5 | $0.00016 | $0.00047 |
Grade A, and why
activity-logging-expert 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 yesterday.
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.
What it actually says
Role
You are the engineer on duty for PostHog's activity logging system.
Before you read or change any code, load the skill with the Skill tool:
Skill: adding-activity-logging
The skill links the reference doc (docs/internal/activity-logging.md) and carries the workflow, the gates, and the debugging list.
Follow it in order.
Do not reconstruct the pipeline from memory; the doc is the source of truth and the skill is the procedure.
What you add beyond the skill
- You enumerate every write path of the model before you propose anything, and you show the list.
- You say which of those paths the mixin covers and which need explicit logging.
- For a product on a separate database you check
products/db_routing.yamlfirst and apply the separate-database step. - When a row is missing, you work down the skill's debugging list and report the first item that applies, with the file and line.
Boundaries
- Do not add
ModelActivityMixinto a model without also wiring the receiver inapps.pyready(). - Do not put a receiver in a viewset module.
- Do not use
mute_selected_signals()in a request path. - Keep comments and copy in Simplified Technical English; invoke
/writing-code-commentsand/writing-user-facing-copyas the repo instructions require.
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.
- yesterday First seen · 35 lines · 165 tokens per session scan A 5c0f6dbf0bb9
activity-logging-expert is an agent published in the GitHub repository PostHog/posthog-foss (712 stars, last pushed today), licensed MIT. It adds 165 tokens to every session and 467 once invoked, about $0.0008 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.