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.
npx skills add nexus-labs-automation/agent-observability --skill tool-call-trackinggit clone --depth 1 https://github.com/nexus-labs-automation/agent-observabilityWrote 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.
[](https://agentmods.dev/skills/nexus-labs-automation/agent-observability/tool-call-tracking)<a href="https://agentmods.dev/skills/nexus-labs-automation/agent-observability/tool-call-tracking"><img src="https://agentmods.dev/badge/skills/nexus-labs-automation/agent-observability/tool-call-tracking/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.
<a href="https://agentmods.dev/skills/nexus-labs-automation/agent-observability/tool-call-tracking"><img src="https://agentmods.dev/badge/skills/nexus-labs-automation/agent-observability/tool-call-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.01207 |
| Opus 5 | $0.00008 | $0.00603 |
| Sonnet 5 | $0.00003 | $0.00241 |
| Haiku 4.5 | $0.00002 | $0.00121 |
Grade A, and why
tool-call-tracking 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Call Tracking
Instrument tool/function executions to understand what agents do and why they fail.
Core Principle
Tools are where agents interact with the real world. Track:
- Which tool was called
- What arguments were passed (safely)
- What result was returned (safely)
- Did it succeed or fail
- How long it took
Essential Span Attributes
# Required (P0)
span.set_attribute("tool.name", "web_search")
span.set_attribute("tool.success", True)
span.set_attribute("tool.latency_ms", 450)
# Safe argument summary (P1)
span.set_attribute("tool.args.query", "weather in NYC") # Safe to log
span.set_attribute("tool.args.count", 3) # Summarize, don't dump
# Result summary (P1)
span.set_attribute("tool.result.type", "search_results")
span.set_attribute("tool.result.count", 10)
span.set_attribute("tool.result.length", 2500)
# Error context (when applicable)
span.set_attribute("tool.error.type", "timeout")
span.set_attribute("tool.error.message", "Request timed out after 30s")
What NOT to Log
# BAD - Full arguments (PII risk, unbounded size)
span.set_attribute("tool.args", json.dumps(args))
span.set_attribute("tool.result", json.dumps(result))
# BAD - Sensitive tool arguments
span.set_attribute("tool.args.api_key", api_key)
span.set_attribute("tool.args.password", password)
# GOOD - Safe summaries
span.set_attribute("tool.args.has_credentials", True)
span.set_attribute("tool.result.success", True)
Tool Categories
Different tools need different instrumentation:
Search/Retrieval Tools
span.set_attribute("tool.name", "vector_search")
span.set_attribute("tool.retrieval.query_length", len(query))
span.set_attribute("tool.retrieval.results_count", len(results))
span.set_attribute("tool.retrieval.top_score", results[0].score)
API/HTTP Tools
span.set_attribute("tool.name", "http_request")
span.set_attribute("tool.http.method", "POST")
span.set_attribute("tool.http.url", sanitize_url(url)) # Remove query params
span.set_attribute("tool.http.status", 200)
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.
- 10d ago First seen · 191 lines · 15 tokens per session scan A 5efde406c266
tool-call-tracking is a skill published in the GitHub repository nexus-labs-automation/agent-observability (7 stars, last pushed 8mo ago), licensed MIT. It adds 15 tokens to every session and 1,207 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…