agentmods.dev

system-observe

system-observe is a skill for Claude Code, Codex from danielwpz/pokoclaw. It costs 54 tokens per session (1,244 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 140repo changed 1mo ago A scan SkillSpector: pass 54 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/github.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/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.

agentmods 80×15 button for system-observe

Your own site · 80×15
<a href="https://agentmods.dev/skills/danielwpz/pokoclaw/system-observe"><img src="https://agentmods.dev/badge/skills/danielwpz/pokoclaw/system-observe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,244 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 $0.00054 $0.01244
Opus 5.5 $0.00022 $0.00498
Sonnet 5.5 $0.00011 $0.00249
Haiku 4.5 $0.00005 $0.00124

Measured 1mo ago against content hash c2e768092120, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

skills/system-observe/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 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
      • ../../src/storage/migrate/files/0004_shell_process_runs.sql
      • ../../src/storage/migrate/files/0005_shell_process_output_chunks.sql
      • ../../src/storage/migrate/files/0006_context_clear.sql
      • ../../src/storage/migrate/files/0007_context_clear_recovery.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 · 82 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. 1mo ago Changed · +7 lines · +9 tokens per session c2e768092120
  2. 2mo 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 (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,244 once invoked, about $0.0002 per session on Opus 5.5. 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

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

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

cwv-optimizer

Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…

adobe/skills · 112 tokens

ci-fixer

CI failures - read error, minimal fix, verify.

sipyourdrink-ltd/bernstein · 15 tokens

incident-response-incident-response

Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.

rmyndharis/antigravity-skills · 36 tokens

diagnosing-missing-recordings

Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…

PostHog/posthog · 76 tokens