agent-observability

agent-observability is a skill for Claude Code, Codex from paruff/uFawkesAI. It costs 38 tokens per session (588 once invoked), scanned A, original, MIT.

A guide for recording and reading telemetry about coding-agent activity. Telemetry is information about what an agent did, such as when it started, loaded a skill, made a decision, or failed.

In plain words
What is it for?
Instrumenting an agent system and analyzing its behavior. It covers events for invocations, loaded skills, findings, decisions, completions, and errors.
Why use it?
It makes agent behavior visible so teams can investigate failures and understand how work is progressing. It uses structured events instead of relying only on informal logs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

Good fit Instrumenting an agent system and analyzing its behavior. It covers events for invocations, loaded skills, findings, decisions, completions, and errors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/paruff/ufawkesai/agent-observability
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 paruff/uFawkesAI --skill agent-observability
Clone the repo
git clone --depth 1 https://github.com/paruff/uFawkesAI

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 agent-observability

README.md
[![agentmods](https://agentmods.dev/badge/skills/paruff/ufawkesai/agent-observability/github.svg)](https://agentmods.dev/skills/paruff/ufawkesai/agent-observability)
Your own site
<a href="https://agentmods.dev/skills/paruff/ufawkesai/agent-observability"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/agent-observability/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 agent-observability

Your own site · 80×15
<a href="https://agentmods.dev/skills/paruff/ufawkesai/agent-observability"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/agent-observability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 588 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 $0.00038 $0.00588
Opus 5 $0.00019 $0.00294
Sonnet 5 $0.00008 $0.00118
Haiku 4.5 $0.00004 $0.00059

Measured 8d ago against content hash f719c0636e55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-observability 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 8d 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/skills/agent-observability/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Agent Observability

Load trigger: "load agent-observability skill" > DORA: Cap 2 (Observability) + Cap 6 (Reliability) Token cost: Low

Purpose

Instrument the agent system itself with the same observability standards applied to application code. Agent actions become observable, measurable, and improvable.

Agent Telemetry Span Types

Span Name When to Emit Attributes
agent.invocation.started Agent begins its task agent.name, session_id, mode
agent.skill.loaded Skill file is loaded for context skill.name, skill.domain
agent.finding.produced A finding is identified severity, category, actionable, manual_review_needed
agent.decision.made Agent produces its final decision decision, blocker_count, finding_count
agent.invocation.completed Agent finishes its task duration_ms, total_skills_loaded, total_findings
agent.invocation.failed Agent encounters an error error, stage

Relation to Phase 0 Logging

Phase 0 logs (.agents/logs/YYYY-MM-DD.jsonl) are the data source. Agent telemetry spans are the OTEL representation of the same events.

Mapping:

  • agent.invocation.started + agent.invocation.completed → one log entry
  • agent.skill.loadedskills_loaded[] array in log entry
  • agent.finding.produced → each item in findings[] array
  • agent.decision.madedecision and blockers fields

Sub-Skills

Skill Purpose
agent-observability/invocation-tracking Track agent start, completion, and duration
agent-observability/skill-load-events Track which skills are loaded and how often
agent-observability/finding-quality Measure finding actionability and accuracy
agent-observability/decision-logging Log agent decisions for post-hoc analysis

Read the full file on GitHub · 50 lines

Files

What ships with it

4 files 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. 8d ago First seen · 50 lines · 38 tokens per session scan A f719c0636e55

Subscribe to this mod's changes

agent-observability is a skill published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 16d ago), licensed MIT. It adds 38 tokens to every session and 588 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 2026-08-31.

Related

Other skills, from other repositories

planning-with-files

Persistent file-based planning for multi-step AI-agent work. Keeps taskplan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and…

mxyhi/ok-skills · 117 tokens

infrastructure-overview

Top-level skill for the research template infrastructure layer. Use in Cursor, Claude Code, or similar agents when editing or importing anything under infrastructure/, understanding the two-layer architecture, or wiring build/validation/rendering/publishing. Covers module discovery, import patterns, thin…

docxology/template · 80 tokens

infrastructure-validation

Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.

docxology/template · 54 tokens

infrastructure-llm

Skill for the LLM infrastructure module providing local Large Language Model integration via Ollama. Covers client initialization, prompt templates, output validation, manuscript review generation, conversation context, and CLI usage. Use when querying LLMs, generating manuscript reviews, validating LLM outputs, or…

docxology/template · 66 tokens

research-workflow

Seven-stage research workflow (SCOPE→LITERATURE→REASON→DESIGN→COMPUTE→SYNTHESIZE→WRITE). Use for: structuring an AI agent's research process, generating literature review prompts, scoping methodology. Usage: from infrastructure.research import ResearchWorkflow; ResearchWorkflow.describe() Config: set stage overrides…

docxology/template · 91 tokens

infrastructure-search-literature

Paperclip-style multi-source literature search across arXiv, Crossref, local JSON corpora, and (opt-in) the Paperclip API. Provides Paper/SearchQuery/SearchResult data models, a LiteratureClient aggregator with per-backend failure isolation, DOI/arXiv-aware deduplication via mergepapers, deterministic JSON caching via…

docxology/template · 123 tokens