agentmods.dev

o11y-review

o11y-review is a skill for Claude Code, Codex from chipi/agentic-ai-homelab. It costs 123 tokens per session (890 once invoked), scanned A, original, MIT.

A read-only report that examines one project’s logs, errors, traces, and repository activity over a chosen time period. Logs are recorded application events, errors are failures, and traces show how requests move through a system.

In plain words
What is it for?
Use it to investigate a project’s health, compare new and older errors, find slow operations or outbound calls, and create an optional handover note for another engineer.
Why use it?
It brings several operational signals into one review without changing the systems being examined. This makes it easier to spot recurring warnings, new failures, slow operations, and recent response work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

not rated 2repo +1 today A scan 123 tokens original MIT

Good fit Use it to investigate a project’s health, compare new and older errors, find slow operations or outbound calls, and create an optional handover note for another engineer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chipi/agentic-ai-homelab/o11y-review
View source ↗ chipi/agentic-ai-homelab
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 chipi/agentic-ai-homelab --skill o11y-review
Clone the repo
git clone --depth 1 https://github.com/chipi/agentic-ai-homelab

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 o11y-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/o11y-review/github.svg)](https://agentmods.dev/skills/chipi/agentic-ai-homelab/o11y-review)
Your own site
<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/o11y-review"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/o11y-review/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 o11y-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/o11y-review"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/o11y-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 890 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 $0.00123 $0.00890
Opus 5.5 $0.00049 $0.00356
Sonnet 5.5 $0.00025 $0.00178
Haiku 4.5 $0.00012 $0.00089

Measured 14d ago against content hash d50e69e26c23, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

o11y-review 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 14d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/review.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

workstation/claude/skills/o11y-review/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

o11y-review

One project, one window, the observability lens. It's read-only: queries only, no writes anywhere.

Run

python3 ~/.claude/skills/o11y-review/scripts/review.py --project closelistening --since 16h
python3 ~/.claude/skills/o11y-review/scripts/review.py --project orrery \
    --start 2026-10-01T18:00:00Z --end 2026-10-02T08:00:00Z --handover /tmp/handover.md

Projects: closelistening (alias podcast), orrery, homelab. To add one, add an entry to PROJECTS in the script:

  • logs: a VictoriaLogs filter;
  • glitchtip: GlitchTip short-id prefixes;
  • traces: trace service names;
  • repo: the GitHub repo the fleet files into.

Access: the stack's ports are loopback-only on the homelab host, so the queries run there over SSH.

  • SSH: the default is the Mac mini (ssh -i ~/.ssh/homelab_mini -o IdentitiesOnly=yes markodragoljevic@homelab); override with --ssh / HOMELAB_SSH.
  • GlitchTip: the token is read on the host from ~/signal-fleet/fleet-gateway.env and is never printed.
  • Fleet actions: come from local gh.

It took about 16 s for a 14-hour Close Listening window (2026-10-02).

Then: read it like an engineer, not a counter

  1. Systematic beats loud. A warning in 26 of 28 runs matters more than one error. Look at the "streams" column.
  2. New beats old. A NEW GlitchTip issue first seen in the window is the first thing to explain.
  3. Traces show where time went: the slowest outbound calls name the bottleneck service. If the report says "API cap 1000 hit", the trace numbers are partial.
  4. Check before claiming. Open the actual log lines in VictoriaLogs (_time:[start, end] <filter> "<pattern words>") before calling a pattern a bug. Normalization merges lines; read real examples.
  5. Hand over facts, not guesses. With --handover, the report is written as-is. Before sending it, add the things you checked yourself and a "not verified" list, e.g. whether an affected item was lost or retried.

Read the full file on GitHub · 46 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 14d ago First seen · 46 lines · 123 tokens per session scan A d50e69e26c23

Subscribe to this mod's changes

o11y-review is a skill published in the GitHub repository chipi/agentic-ai-homelab (2 stars, last pushed today), licensed MIT. It adds 123 tokens to every session and 890 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-03.

Analytics and metricsClaude CodeDebuggingagentic-aigrafana-alloyhomelablibrechatmcp
Related

Other skills, from other repositories

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

cvm-ai-doctor

A health-diagnosis workflow for servers, computers, virtual machines, and containers on Linux, macOS, or Windows.

TencentCloud/Octop · 60 tokens

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens

ai-discover

Read-only discovery step of the auto-improvement loop. One bounded agent turn per cycle reads the focus files (Read/Grep/Glob only, no shell, no subagents) and replies with a JSON array of testable surfaces {file, line, symbol, rule, message, hypothesis}; the spine authors fixes and verifies them. Discovery only — no…

kirodotdev/KiroCrew · 83 tokens

hns-lsel-curator

Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…

modu-ai/moai-adk · 135 tokens