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 error-retry-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/error-retry-tracking)<a href="https://agentmods.dev/skills/nexus-labs-automation/agent-observability/error-retry-tracking"><img src="https://agentmods.dev/badge/skills/nexus-labs-automation/agent-observability/error-retry-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/error-retry-tracking"><img src="https://agentmods.dev/badge/skills/nexus-labs-automation/agent-observability/error-retry-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 | $0.00018 | $0.01816 |
| Opus 5 | $0.00009 | $0.00908 |
| Sonnet 5 | $0.00004 | $0.00363 |
| Haiku 4.5 | $0.00002 | $0.00182 |
Grade A, and why
error-retry-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 9d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error and Retry Tracking
Instrument error handling to understand failure patterns and recovery behavior.
Core Principle
Error observability answers:
- What failed and why?
- How many retries before success/failure?
- What fallbacks were used?
- What's the recovery rate?
- Are errors correlated (rate limits, outages)?
Error Classification
Transient vs. Permanent
TRANSIENT_ERRORS = [
"RateLimitError",
"TimeoutError",
"ServiceUnavailable",
"ConnectionError",
]
PERMANENT_ERRORS = [
"InvalidRequestError",
"AuthenticationError",
"ContentPolicyViolation",
"ContextLengthExceeded",
]
def classify_error(error: Exception) -> str:
error_type = type(error).__name__
if error_type in TRANSIENT_ERRORS:
return "transient"
elif error_type in PERMANENT_ERRORS:
return "permanent"
return "unknown"
Error Span Attributes
# Error identification (P0)
span.set_attribute("error.type", "RateLimitError")
span.set_attribute("error.message", "Rate limit exceeded")
span.set_attribute("error.category", "transient")
span.set_attribute("error.source", "llm_provider")
# Provider context (P1)
span.set_attribute("error.provider", "anthropic")
span.set_attribute("error.model", "claude-3-opus")
span.set_attribute("error.status_code", 429)
span.set_attribute("error.request_id", "req_abc123")
# Timing context (P1)
span.set_attribute("error.retry_after_ms", 60000)
span.set_attribute("error.occurred_at_step", 3)
span.set_attribute("error.time_into_request_ms", 2500)
# Impact (P2)
span.set_attribute("error.tokens_wasted", 1500) # Tokens sent before failure
span.set_attribute("error.cost_wasted_usd", 0.015)
Retry Span Attributes
# Retry tracking (P0)
span.set_attribute("retry.attempt", 2)
span.set_attribute("retry.max_attempts", 3)
span.set_attribute("retry.strategy", "exponential_backoff")
# Timing (P1)
span.set_attribute("retry.delay_ms", 2000)
span.set_attribute("retry.total_wait_ms", 3500)
span.set_attribute("retry.jitter_ms", 150)
# Outcome (P0)
span.set_attribute("retry.success", True)
span.set_attribute("retry.final_attempt", 2)
span.set_attribute("retry.exhausted", False)
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.
- 9d ago First seen · 269 lines · 18 tokens per session scan A e683274e7233
error-retry-tracking is a skill published in the GitHub repository nexus-labs-automation/agent-observability (7 stars, last pushed 8mo ago), licensed MIT. It adds 18 tokens to every session and 1,816 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.