agentmods.dev

observe

An observability agent for recording and inspecting what happens during agent runs. Observability means keeping evidence about events, progress, costs, and outcomes so work can be understood later.

In plain words
What is it for?
Use it to inspect event logs, checkpoints, traces, metrics, project status, intervention history, deployment completion, and rollback evidence.
Why use it?
It provides a durable record when a run must be resumed, traced, measured, or checked against what actually happened.

Agent

5 13d ago A scan 0 tokens original MIT
View the source file hannsxpeter/godpowers
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/hannsxpeter/godpowers/observe
Clone the repo
git clone --depth 1 https://github.com/hannsxpeter/godpowers
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 709 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 $0.00000 $0.00709
Opus 5 $0.00000 $0.00354
Sonnet 5 $0.00000 $0.00142
Haiku 4.5 $0.00000 $0.00071

Measured 2d ago against content hash 02230d1da195, 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 2d 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/observe.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope

  • [DECISION] This pillar captures observability mechanisms inside Godpowers itself.

Context

Signals

  • [DECISION] lib/events.js writes hash-chained JSONL events under .godpowers/runs/<run-id>/events.jsonl.
  • [DECISION] lib/checkpoint.js writes .godpowers/CHECKPOINT.mdx as the durable orientation pin for future sessions.
  • [DECISION] /god-logs, /god-metrics, and /god-trace read the event stream.
  • [DECISION] lib/outcome-metrics.js derives time to accepted change, recorded cost, manual intervention, resume success, deployment completion, and rollback proof without filling absent evidence.
  • [DECISION] lib/dashboard.js renders disk-derived project status, action brief, proactive checks, and host guarantees.
  • [DECISION] Event vocabulary includes local helper, dashboard, host capability, dogfood, source-system import, sync-back, repo-doc sync, and repo-surface sync events.
  • [DECISION] context.loadout events preserve complete loaded and omitted counts plus bounded source identifiers without recording file or inline contents.
  • [DECISION] lib/slice-handoff.js derives an at-most-8-KiB resume projection from authoritative plan, state, event, linkage, and verification evidence.
  • [DECISION] Evolution benchmark evidence records behavior, attempts, rework, changed lines, acceptance, handoff completeness, and maintainability deltas for each of six ordered checkpoints.
  • [DECISION] decision.recorded events use the existing hash chain, and /god-trace --decisions returns a bounded read-only { items, integrityFailures } projection from one verified snapshot per selected run.

Decisions

  • [DECISION] Pull-request CI run 32271677551 and merged-main CI run 32272127234 passed for the exact 6.3.0 release tree.
  • [DECISION] Provenance workflow 32272150358 passed in 2 minutes 38 seconds and published the exact 6.3.0 root and MCP pair.
  • [DECISION] Provenance workflow 32272475321 passed in 2 minutes 17 seconds and published the exact operations pack.
  • [DECISION] Publication verification records observed release evidence without claiming unavailable production-user outcomes.

Read the full file on GitHub · 65 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. 2d ago First seen · 65 lines · 0 tokens per session scan A 02230d1da195

Subscribe to this mod's changes

observe is an agent published in the GitHub repository hannsxpeter/godpowers (5 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 709 tokens. 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.

Analytics and metricsDevOps and cloudagent-orchestrationai-codingclaude-codecodexcursordeveloper-tools
Related

Other agents, from other repositories

ap-framework-generator

L3 executor - FRAMEWORK GENERATE. When the SELECTOR returns MISS, generates a one-off custom framework for the exact task shape - classifies the orthogonal axes, composes the gate sequence from the GATE-LIBRARY with the correct axis-specific gate, emits the gen- leaf with the BLOCKED invariant verbatim, binds an…

Spielewoy/autoprompt-skill · 93 tokens

ap-juror

L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.

Spielewoy/autoprompt-skill · 58 tokens

ap-re-anchor

L4 terminal leaf - RE-ANCHOR. Confirms mission and roadmap frontier alignment after resume or compaction using the three-file governance state.

Spielewoy/autoprompt-skill · 33 tokens

ap-verifier

L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.

Spielewoy/autoprompt-skill · 35 tokens

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase. This is a single-context repo.

h0x91b/dev-3.0 · 0 tokens

ijfw-extract-learnings

Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.

FerroxLabs/ijfw · 31 tokens