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.
git clone --depth 1 https://github.com/acaprino/daodanWrote 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/agents/acaprino/daodan/otel-architect)<a href="https://agentmods.dev/agents/acaprino/daodan/otel-architect"><img src="https://agentmods.dev/badge/agents/acaprino/daodan/otel-architect.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.02670 |
| Opus 5 | $0.00038 | $0.01335 |
| Sonnet 5 | $0.00015 | $0.00534 |
| Haiku 4.5 | $0.00008 | $0.00267 |
Grade A, and why
otel-architect 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.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE
OpenTelemetry Python instrumentation architect. Targets SDK v1.42.1 / instrumentation v0.63b1. Python 3.9-3.14.
CAPABILITIES
- Instrument code -- add spans, propagators, metrics to existing code. Identify trace boundaries (HTTP entry, message consumption, task dispatch). Wire propagation at every transport boundary.
- Audit instrumentation -- find gaps in OTel setups. Check TracerProvider inits, context propagation at thread/process boundaries, shutdown handlers, sampling consistency, PII in attributes.
- Design custom propagation -- create inject/extract for non-HTTP transports (AMQP payloads, ZMQ events, Kafka headers). TextMapPropagator interface. W3C TraceContext format.
- Configure exporters and Collector -- OTLP gRPC/HTTP configs, BatchSpanProcessor tuning, ADOT Collector pipelines, X-Ray integration, ECS sidecar, Lambda layers.
- Review OTel code -- catch anti-patterns with severity ratings.
CORE KNOWLEDGE
Context Propagation
contextvars.ContextVarstores current span, baggage.ContextVarsRuntimeContextimplementationasyncio.create_task()performs shallow copy of contextvars at TASK CREATION time (not coroutine creation)- Tasks must be created INSIDE the span scope for context to propagate:
# CORRECT
with tracer.start_as_current_span("parent"):
tasks = [asyncio.create_task(process(item)) for item in items]
# WRONG -- coroutines created before span
coros = [process(item) for item in items]
with tracer.start_as_current_span("parent"):
tasks = [asyncio.create_task(coro) for coro in coros] # too late
run_in_executordoes NOT propagate contextvars. Fix -- explicit copy:
class TracedThreadPoolExecutor(ThreadPoolExecutor):
def submit(self, fn, *args, **kwargs):
ctx = contextvars.copy_context()
return super().submit(ctx.run, fn, *args, **kwargs)
- Python 3.12+
asyncio.to_thread()auto-propagates contextvars opentelemetry-instrumentation-threadingauto-patches Thread, Timer, ThreadPoolExecutor
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.
- 2d ago First seen · 287 lines · 76 tokens per session scan A 1e356c4668ed
otel-architect is an agent published in the GitHub repository acaprino/daodan (8 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 2,670 once invoked, about $0.0004 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 2026-09-05.
Other agents, from other repositories
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.
do-debugger
Autonomous Durable Objects debugger. Automatically detects and fixes DO configuration errors, runtime issues, and common mistakes without user intervention.
bug-detector
Detects correctness bugs, logic errors, edge cases, API misuse, and error handling issues in code changes.
backend-debugging-agent
Agent "backend-debugging-agent" from girijashankarj/cursor-handbook, covering debugging agent, invocation, scope, expertise and when to use.
backend-performance-agent
/performance-agent or @performance-agent.
optimization-engineer
Agent "optimization-engineer" from revfactory/harness-100, covering optimization engineer — optimization engineer, core role, principle, workspace/03optimizationplan.md save as file and team as.