observer

A background agent that reviews recorded coding-session events to find repeated patterns and create project-specific or global instincts, meaning reusable observations about how work is done.

In plain words
What is it for?
Use it to analyze observations such as tool starts, tool results, sessions, and project identifiers from JSONL files.
Why use it?
It turns accumulated session observations into guidance that can inform later work. It can run after enough observations, on a schedule, or when requested by a process signal.

Agent

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.

agentmods
npx agentmods add agents/x-cmd/skill/observer
Clone the repo
git clone --depth 1 https://github.com/x-cmd/skill
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,883 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.01883
Opus 5 $0.00016 $0.00941
Sonnet 5 $0.00007 $0.00377
Haiku 4.5 $0.00003 $0.00188

Measured yesterday against content hash 654f2f0fc9d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

observer 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 yesterday.

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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

  • observer — 100% identical, 0 lines differ
  • observer — 100% identical, 18 lines differ
  • observer — 100% identical, 0 lines differ
  • observer — 86% identical, 8 lines differ
data/affaanmustafa/continuous-learning-v2/agents/observer.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Observer Agent

A background agent that analyzes observations from Claude Code sessions to detect patterns and create instincts.

When to Run

  • After enough observations accumulate (configurable, default 20)
  • On a scheduled interval (configurable, default 5 minutes)
  • When triggered on demand via SIGUSR1 to the observer process

Input

Reads observations from the project-scoped observations file:

  • Project: ~/.claude/homunculus/projects/<project-hash>/observations.jsonl
  • Global fallback: ~/.claude/homunculus/observations.jsonl
{"timestamp":"2025-01-22T10:30:00Z","event":"tool_start","session":"abc123","tool":"Edit","input":"...","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
{"timestamp":"2025-01-22T10:30:01Z","event":"tool_complete","session":"abc123","tool":"Edit","output":"...","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
{"timestamp":"2025-01-22T10:30:05Z","event":"tool_start","session":"abc123","tool":"Bash","input":"npm test","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}
{"timestamp":"2025-01-22T10:30:10Z","event":"tool_complete","session":"abc123","tool":"Bash","output":"All tests pass","project_id":"a1b2c3d4e5f6","project_name":"my-react-app"}

Pattern Detection

Look for these patterns in observations:

1. User Corrections

When a user's follow-up message corrects Claude's previous action:

  • "No, use X instead of Y"
  • "Actually, I meant..."
  • Immediate undo/redo patterns

→ Create instinct: "When doing X, prefer Y"

2. Error Resolutions

When an error is followed by a fix:

  • Tool output contains error
  • Next few tool calls fix it
  • Same error type resolved similarly multiple times

→ Create instinct: "When encountering error X, try Y"

3. Repeated Workflows

When the same sequence of tools is used multiple times:

  • Same tool sequence with similar inputs
  • File patterns that change together
  • Time-clustered operations

→ Create workflow instinct: "When doing X, follow steps Y, Z, W"

Read the full file on GitHub · 199 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. yesterday First seen · 199 lines · 33 tokens per session scan A 654f2f0fc9d9

Subscribe to this mod's changes

observer is an agent published in the GitHub repository x-cmd/skill (26 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,883 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.