agentmods.dev

system-observe

system-observe is a skill for Claude Code, Codex from danielwpz/pokoclaw. It costs 45 tokens per session (1,052 once invoked), scanned A, original, Apache-2.0.

A guide for inspecting the Pokoclaw agent system through its database, runtime logs, and source definitions.

In plain words
What is it for?
Checking live runs, reviewing errors and retries, investigating approvals, and diagnosing scheduled or background work.
Why use it?
It helps explain what the system is doing, including active runs, failures, approvals, and tasks that appear stuck.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 141repo 20d ago A scan SkillSpector: pass 45 tokens original Apache-2.0

Good fit Checking live runs, reviewing errors and retries, investigating approvals, and diagnosing scheduled or background work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielwpz/pokoclaw/system-observe
View source ↗ danielwpz/pokoclaw
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.

Any agent
npx skills add danielwpz/pokoclaw --skill system-observe
Clone the repo
git clone --depth 1 https://github.com/danielwpz/pokoclaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for system-observe

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielwpz/pokoclaw/system-observe.svg)](https://agentmods.dev/skills/danielwpz/pokoclaw/system-observe)
Your own site
<a href="https://agentmods.dev/skills/danielwpz/pokoclaw/system-observe"><img src="https://agentmods.dev/badge/skills/danielwpz/pokoclaw/system-observe.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,052 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01052
Opus 5 $0.00023 $0.00526
Sonnet 5 $0.00009 $0.00210
Haiku 4.5 $0.00005 $0.00105

Measured 9d ago against content hash a97a01fd7bcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

system-observe 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 9d 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.

skills/system-observe/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Observe

Use this skill to inspect pokoclaw itself.

Channels

  • Live runtime status: Main Agent only, global current-running state across active runs, background tasks, cron task runs, and suspect durable rows that still claim to be running without a matching live run. Use get_runtime_status first when you need to know what is actively running right now. Use its runId form to inspect one low-level run, including a retained just-finished snapshot when still available in process memory.
  • System database: durable facts such as sessions, messages, task runs, cron jobs, approvals, permission grants, and delegated approval history.
  • Runtime log: host-side operational evidence such as failures, routing decisions, retries, crashes, and subsystem errors.
  • Source code and references: authoritative schema definitions and implementation behavior.
  • Meditation self-harness: a background self-optimization flow. It is not part of the core live run-status surface, but when the question is specifically about whether Meditation ran, why it skipped or failed, or where its artifacts and outputs live, use references/meditation.md.

Choose one or more channels based on the question. Do not force a fixed order for every task.

Required first reads

  • If the task involves database facts, approval history, delegated approval, or SQL:
    • Read references/query-recipes.md first.
    • If exact table or column names matter, read references/schema-overview.md.
    • If that is still insufficient, inspect:
      • ../../src/storage/schema/tables.ts
      • ../../src/storage/schema/types.ts
      • ../../src/storage/migrate/files/0001_init.sql
      • ../../src/storage/migrate/files/0002_agent_runtime_modes.sql
      • ../../src/storage/migrate/files/0003_a2ui_surface_publications.sql The schema truth lives in tables.ts plus the migration SQL files.
    • Only then use query_system_db for live schema discovery.
  • If the task involves live runtime status payload semantics for get_runtime_status:
    • Read references/runtime-status.md first.
  • If the task involves runtime logs:
    • Read references/log-recipes.md first.
  • If the task explicitly involves Meditation or self-harness background runs:
    • Read references/meditation.md first.
  • If the task is really about implementation behavior:
    • Read the relevant source files first, then use DB facts or logs as supporting evidence.

Read the full file on GitHub · 75 lines

Files

What ships with it

5 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.

  1. 9d ago First seen · 75 lines · 45 tokens per session scan A a97a01fd7bcc

Subscribe to this mod's changes

system-observe is a skill published in the GitHub repository danielwpz/pokoclaw (141 stars, last pushed 20d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,052 once invoked, about $0.0002 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 2026-08-30.

Debugging
Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens