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 JansenAnalytics/claudex --skill event-loggit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/jansenanalytics/claudex/event-log)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/event-log"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/event-log.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 5.1 | $0.00023 | $0.00846 |
| Opus 5 | $0.00012 | $0.00423 |
| Sonnet 5 | $0.00005 | $0.00169 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
event-log 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 3d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
event-log
An append-only structured JSONL event log giving Kite continuity across sessions — without reading every log file.
What it does
Writes structured events to ~/.openclaw/events.jsonl. Each event captures a timestamp, type, session ID, human-readable summary, and optional metadata. Kite can query the log at the start of any session to instantly know what happened recently.
Event file
~/.openclaw/events.jsonl
Each line is one JSON event:
{
"ts": "2026-02-21T17:00:00Z",
"type": "note",
"session": "agent:main:abc",
"summary": "Gateway auth fixed",
"meta": {}
}
Script location
${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs
Also symlinked in skill scripts for reference:
${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/event-log/scripts/event-log.cjs
CLI usage
# Log an event
node ${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs log \
--type note --summary "Started working on X"
# With metadata
node ${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs log \
--type notification_sent \
--summary "Sent stock alert" \
--meta '{"channel":"telegram","topic":"stock"}'
# View last 20 events
node ${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs tail
# View last 50
node ${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs tail --n 50
# Events from today
node ${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs today
# Search summaries
node ${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs search "stock"
# Filter by type
node ${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs type notification_sent
# Events since a date
node ${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs since "2026-02-21"
# Stats: counts by type, today/week
node ${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs stats
Programmatic API
const { logEvent } = require("${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs");
logEvent("notification_sent", "Stock alert fired", { channel: "telegram" });
logEvent("cron_ran", "web-monitor check complete", { success: true, duration_ms: 312 });
logEvent("error", "Failed to reach Eric Bloodaxe URL", { url: "https://...", code: 503 });
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.
- 3d ago First seen · 123 lines · 23 tokens per session scan A 75523d5b483d
event-log is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 846 once invoked, about $0.0001 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 skills, from other repositories
liquefy-archive
Background compression and vault archival for OpenClaw workspaces — auto-packs sessions, memory, and artifacts into verified .null vaults with full MRTV proofs. Blocks credential and key leaks before archiving.
cross-agent-handoff
Transfer context between AI agent sessions with structured handoff protocols, state serialization, and decision log preservation. Covers multi-agent coordination, context compression, and continuity patterns. Triggers on agent handoff, session transfer, or multi-agent continuity requests.
liquefy-openclaw
Use this skill when working with Liquefy around OpenClaw, including plugin scan/apply flows, native hook integration, session vaulting, search/restore, policy explanation, guarded runs, context gate, replay blocking, and state/history guard workflows.
context-capsule
Compresses older OpenClaw agent session history into a bounded, lane-change-aware context capsule — keeps recent messages verbatim, flags abandoned directions, quarantines injected instructions, and redacts secrets. Local, deterministic, any model.
brain-save
Saves a single fact, decision, pattern, or convention into your governed knowledge brain so it can be recalled later — and retires memories that are outdated. Side-effecting: it writes to your durable corpus, so it never auto-fires — invoke it explicitly. Use when you want the brain to remember something specific…
brain
Answers questions about your own systems, notes, decisions, runbooks, and conventions from your governed knowledge brain, returning a qmd:// citation for every claim — receipts, not recall. Use when you want to know what your brain has captured about your own architecture, infrastructure, decisions, or conventions…