agentleFS
fmindfmind/dot/skills/pup/SKILL.md

pup

Skill13 starsChanged yesterdayMITView on GitHub

Query Datadog logs, metrics, traces, monitors, incidents, and LLM observability with pup.

  • Reads credentials

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use pup with OAuth2 PKCE (pup auth login --read-only --site <site> [--org <name>]), never long-lived DD_API_KEY/DD_APP_KEY env vars unless …

    line 15
  2. Very specific:

    Never auto-trust unknown gateways: only pass --trust-site after the user explicitly verifies a non-Datadog gateway host.

    line 32
  3. Very specific:

    Never dump credentials: never inspect ~/.config/pup/ or print secrets from pup api-keys / pup app-keys.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Datadog (pup)

Use pup with OAuth2 PKCE (pup auth login --read-only --site <site> [--org <name>]), never long-lived DD_API_KEY/DD_APP_KEY env vars unless CI requires service-account keys. Tokens live in ~/.config/pup/ (0600).

Commands

pup auth status --site datadoghq.eu
pup --read-only --no-envelope logs search --query "status:error service:api" --from 1h --to now --limit 50
pup --read-only --jq '.data' metrics query --query "avg:system.cpu.user{*}" --from 1h --to now
pup --read-only monitors list --limit 25
  • Pass --read-only on investigative/triage runs to block writes client-side; wrap --no-envelope (PUP_NO_ENVELOPE=1) and --jq '<expr>' to unwrap {status, data, metadata}.
  • Redirected pipes keep JSON (-o json); --verbose logs rate-limit headers to stderr. Pin DD_SITE/--site and --org <name> explicitly.

Guardrails

  • Always bound windows and counts: specify --from/--to and --limit on logs, traces, ddsql, rum, and llm-obs queries before summarizing.
  • Never auto-trust unknown gateways: only pass --trust-site after the user explicitly verifies a non-Datadog gateway host.
  • Never dump credentials: never inspect ~/.config/pup/ or print secrets from pup api-keys / pup app-keys.
  • Ask before writes or external AI routing: require approval before -y, creating/mutating monitors, downtime, incidents, dashboards, workflows, data-deletion, or sending internal context to pup bits / pup acp.

Documentation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.