observe

A command for investigating a software problem using logs, measurements, and traces, which record what a system did and how requests moved through it.

In plain words
What is it for?
Use it to inspect a target service or system area, review its logs, metrics, and traces, and attach supporting evidence to a validation session.
Why use it?
It keeps the investigation tied to the project’s validation plan and records evidence, blockers, and the next action in the expected session files.

Command

Part of the openarche plugin — 11 commands shipped together

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 commands/done-0/openarche/observe
Clone the repo
git clone --depth 1 https://github.com/Done-0/openarche

Or install openarche, the plugin that ships this one along with the rest of its 11 commands.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 301 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 $0.00011 $0.00301
Opus 5 $0.00005 $0.00151
Sonnet 5 $0.00002 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 3d ago against content hash 9de8471e3ffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

commands/observe.md · 35 lines

What it actually says

Use this command to inspect or update the observability part of the current validation protocol.

Required behavior:

  1. Prefer the current session state in .openarche/sessions/<task-id>/state.json. Observability evidence lives inside runbook.validation, not in a separate maintenance or review file.
  2. Read the current observability spec from runbook.validation.observability when one exists.
  3. Use the spec as the source of truth for:
    • logs
    • metrics
    • traces
    • evidence
    • blockers
    • ready
  4. If the user is attaching observability evidence, add it to runbook.validation.observability, keep the state file valid, and place any file evidence under .openarche/sessions/<task-id>/evidence/.
  5. If the user is only asking for an investigation plan, keep the response aligned to the existing observability spec instead of inventing a different structure.

When presenting the observability work, organize it into:

  • target service or system area
  • objective or failure mode
  • logs to inspect
  • metrics to inspect
  • traces to inspect
  • evidence already attached
  • blockers that still keep observability open
  • next action

Only create a separate note when the user explicitly asks for one.

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. 3d ago First seen · 35 lines · 11 tokens per session scan A 9de8471e3ffa

Subscribe to this mod's changes

observe is a command published in the GitHub repository Done-0/openarche (12 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 301 once invoked, about $0.0001 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.