DataDog/pup is a command-line client that gives AI agents access to Datadog's observability platform. It lets agents retrieve and manage information across Datadog products such as metrics, logs, monitors, RUM, and security data, with structured output for automation.
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 DataDog/pup --skill dd-debuggergit clone --depth 1 https://github.com/DataDog/pupWrote 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/datadog/pup/dd-debugger)<a href="https://agentmods.dev/skills/datadog/pup/dd-debugger"><img src="https://agentmods.dev/badge/skills/datadog/pup/dd-debugger/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/datadog/pup/dd-debugger"><img src="https://agentmods.dev/badge/skills/datadog/pup/dd-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 149 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00052 | $0.02636 |
| Opus 5.5 | $0.00021 | $0.01054 |
| Sonnet 5.5 | $0.00010 | $0.00527 |
| Haiku 4.5 | $0.00005 | $0.00264 |
Grade A, and why
dd-debugger 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 1mo 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Datadog Live Debugger
Place log probes on running services without redeploying. Create probes with custom templates and conditions, and stream captured events in real time.
Prerequisites
pup must be installed:
brew tap datadog-labs/pack && brew install pup
Authentication
Authenticate via OAuth2 (recommended) or API keys:
# OAuth2 (recommended)
pup auth login
# Or use API keys
export DD_API_KEY="key" DD_APP_KEY="key" DD_SITE="datadoghq.com"
Typical Workflow
Prefer --capture expressions over full snapshots. Capture expressions are lighter-weight, faster, and return exactly the data you need.
- If you don't know the service, ask the user before proceeding.
- Verify the service using
pup debugger context <service>to list environments with active instances. If multiple environments exist, ask the user which one to target before proceeding. - Find a method using the
dd-symdbskill (pup symdb search --view probe-locations) - Place a probe with capture expressions for the values you need
- Watch events with
--fieldsfor compact output - Delete the probe when done
# 0. List environments (if multiple, ask user which to use)
pup debugger context my-service --fields service,language,envs
# 1. Create a probe with capture expressions (recommended)
# Use --fields id to get just the probe ID back
pup debugger probes create \
--service my-service \
--env production \
--probe-location "com.example.MyController:handleRequest" \
--capture "request.id" \
--capture "request.headers" \
--ttl 1h \
--fields id
# 2. Stream events with compact output
pup debugger probes watch <PROBE_ID> --timeout 60 --limit 10 \
--fields "message,captures,timestamp"
# 3. Clean up
pup debugger probes delete <PROBE_ID>
Service Context
Always run this before creating probes. It returns JSON by default (like all other commands) showing environments with active instances, tracer versions, and supported probe features. If the service runs in multiple environments, ask the user which one to target — don't guess.
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.
- 1mo ago First seen · 319 lines · 52 tokens per session scan A 1959d3a98fe5
dd-debugger is a skill published in the GitHub repository DataDog/pup (1,030 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 2,636 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
repair-github-ci
Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.
investigating-incidents-with-runbooks
Investigate an incident with organization-owned runbook guidance, loaded by URL or exact alert identity. Multi-step; load before acting.
operating-github-ci-fixer
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
summarizing-sentry-issues
Summarise Sentry issues by theme and impact with optional uptime rollup. For overviews, morning digests, reliability questions.
observability
Use when instrumenting a service from the inside so an incident can be explained from telemetry alone — wiring OpenTelemetry logs, metrics and traces, standing up a Collector, exporting via OTLP, and defining telemetry-driven alerts. NOT outside-in uptime probes, on-call rotation, or who-gets-paged (that is…
elastic
Elastic Cloud (Elasticsearch + Kibana) integration for discovering indices, searching logs with Lucene or ES|QL, and reading Kibana alerts during RCA investigations.