agent-observatory

agent-observatory is a skill for Claude Code, Codex from hams-ollo/zen-agent-skills. It costs 194 tokens per session (1,856 once invoked), scanned A, original, MIT.

A reporting and session-management guide for examining coding-agent sessions across projects. It uses a local observatory store to show session activity, costs, skills, and failures.

In plain words
What is it for?
Use it to find sessions by their work, see which sessions are running, review failures and costs, rename a session, or send it a message when supported.
Why use it?
It helps answer cross-project questions without reading each session transcript one at a time.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Use it to find sessions by their work, see which sessions are running, review failures and costs, rename a session, or send it a message when supported.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hams-ollo/zen-agent-skills/agent-observatory
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 hams-ollo/zen-agent-skills --skill agent-observatory
Clone the repo
git clone --depth 1 https://github.com/hams-ollo/zen-agent-skills

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 agent-observatory

README.md
[![agentmods](https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/agent-observatory/github.svg)](https://agentmods.dev/skills/hams-ollo/zen-agent-skills/agent-observatory)
Your own site
<a href="https://agentmods.dev/skills/hams-ollo/zen-agent-skills/agent-observatory"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/agent-observatory/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 agent-observatory

Your own site · 80×15
<a href="https://agentmods.dev/skills/hams-ollo/zen-agent-skills/agent-observatory"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/agent-observatory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,856 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.
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 $0.00194 $0.01856
Opus 5 $0.00097 $0.00928
Sonnet 5 $0.00039 $0.00371
Haiku 4.5 $0.00019 $0.00186

Measured 6d ago against content hash 0ef6afdffd70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-observatory 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 6d 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.

.agents/skills/agent-observatory/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-observatory

Answer questions that span sessions, and act on a session only where the harness actually lets you. This is the companion to the local reporting surface: the page reports and offers nothing to do, and this skill is where a session-directed action lives when one is available at all.

This skill is a draft. It ships with no profile and reaches no adopter until it has been used on real work and blessed, per the contribution bar in the target repository's AGENTS.md.

When to use

  • A question spans more than one session: what is running, what a wave cost, which skills were used, what failed and how often.
  • You want to find a session by what it did rather than by scrolling a list.
  • You want to rename a session whose title has gone stale, or hand a message to another session.

When not to use

  • You want to start, resume, interrupt, or end a session. This skill does none of those and will not find a way to. Ask the person to run the command themselves.
  • You want the numbers rendered rather than answered in prose. Point them at the local page.
  • The question is about one session you are already in. Just answer it.

Inputs

Required: nothing. The skill reads what it can reach and says what it could not.

Optional:

  • A project scope, to restrict every figure to one project.
  • A session id or a description of one, when the question is about a particular session.

Procedure

1. Establish what you can reach, before answering anything

Two sources, and they answer different questions. Check both and say which one an answer came from, because a reader who cannot tell will assume the stronger one.

Source Answers Reach
The observatory store, built by the ingester in the target repository's scripts/observatory/ history: skills, tokens, waves, health, per-project figures every session whose transcript is on this machine
The harness's own session management, when exposed now: what exists, what is running, what is archived, and the actions below local, remote, and cloud sessions alike

Read the full file on GitHub · 143 lines

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. 6d ago Changed · +7 lines 0ef6afdffd70
  2. 10d ago First seen · 136 lines · 194 tokens per session scan A 87a3cd843a33

Subscribe to this mod's changes

agent-observatory is a skill published in the GitHub repository hams-ollo/zen-agent-skills (2 stars, last pushed 8d ago), licensed MIT. It adds 194 tokens to every session and 1,856 once invoked, about $0.0010 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 2026-08-31.