observations

observations is a skill for Claude Code from kalinbogatzevski/captain-memo. It costs 34 tokens per session (402 once invoked), scanned A, original, Apache-2.0.

A command that lists recent session observations recorded by Captain Memo, such as summaries of earlier coding-agent sessions.

In plain words
What is it for?
Use it to display a chosen number of recent observations, including their time, type, title, session, and prompt number.
Why use it?
It provides a quick view of what was logged previously, without requiring the user to inspect the session history manually.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the captain-memo plugin — 5 skills, 6 hooks shipped together

Good fit Use it to display a chosen number of recent observations, including their time, type, title, session, and prompt number.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kalinbogatzevski/captain-memo/observations
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 kalinbogatzevski/captain-memo --skill observations
Clone the repo
git clone --depth 1 https://github.com/kalinbogatzevski/captain-memo

Made for: Claude Code.

Or install captain-memo, the plugin that ships this one along with the rest of its 5 skills, 6 hooks.

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 observations

README.md
[![agentmods](https://agentmods.dev/badge/skills/kalinbogatzevski/captain-memo/observations/github.svg)](https://agentmods.dev/skills/kalinbogatzevski/captain-memo/observations)
Your own site
<a href="https://agentmods.dev/skills/kalinbogatzevski/captain-memo/observations"><img src="https://agentmods.dev/badge/skills/kalinbogatzevski/captain-memo/observations/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 observations

Your own site · 80×15
<a href="https://agentmods.dev/skills/kalinbogatzevski/captain-memo/observations"><img src="https://agentmods.dev/badge/skills/kalinbogatzevski/captain-memo/observations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00034 $0.00402
Opus 5 $0.00017 $0.00201
Sonnet 5 $0.00007 $0.00080
Haiku 4.5 $0.00003 $0.00040

Measured 9d ago against content hash b563984fbeba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

observations scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "http://127.0.0.1:39888/observations/recent?limit=<LIMIT>" | jq '.'
plugin/skills/observations/SKILL.md · 41 lines

What it actually says

Captain Memo — recent observations

When the user invokes this skill, they want a quick view of recent session observations — the structured "voyage logs" the Stop hook produces.

What to do

  1. Parse the user's argument as --limit N (default 20). If they typed /captain-memo:observations 50, treat 50 as the limit.
  2. Run:
curl -s "http://127.0.0.1:39888/observations/recent?limit=<LIMIT>" | jq '.'
  1. The response is { items: [{id, session_id, prompt_number, type, title, created_at_epoch}] }.

Output format

Recent observations (N total):

  2026-05-07 14:32  [bugfix    ]  Fix off-by-one in billing pro-ration loop
                    session=ses_..._abc123 · prompt#1 · id=42

  2026-05-07 14:18  [feature   ]  Add NetLine SPM rule 75 for Pernik discount
                    session=ses_..._xyz890 · prompt#3 · id=41

  …

Format created_at_epoch as a UTC date in the user's timezone. Pad [type] to 10 chars for alignment.

If empty

Say something like:

"No observations yet. Captain Memo's Stop hook summarises sessions when they end — make sure you've actually closed (/exit) at least one Claude Code session since installing, and that ANTHROPIC_API_KEY or claude-code summarizer is configured. Run captain-memo doctor to verify."

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 · 41 lines · 34 tokens per session scan A b563984fbeba

Subscribe to this mod's changes

observations is a skill published in the GitHub repository kalinbogatzevski/captain-memo (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 34 tokens to every session and 402 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.