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 agentmods add skills/datadog/pup/dd-code-generationnpx skills add DataDog/pup --skill dd-code-generationgit clone --depth 1 https://github.com/DataDog/pupWhat 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 | $0.00016 | $0.04133 |
| Opus 5 | $0.00008 | $0.02067 |
| Sonnet 5 | $0.00003 | $0.00827 |
| Haiku 4.5 | $0.00002 | $0.00413 |
Grade A, and why
dd-code-generation 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 yesterday.
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 — 552 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Datadog Integration Skill
This skill helps users interact with Datadog through two complementary approaches:
- Immediate execution using the
pupCLI tool - Code generation for application integration using Datadog API clients
When to Use This Skill
Use this skill when the user:
- Wants to query Datadog data (logs, traces, metrics, etc.)
- Needs to configure Datadog (monitors, dashboards, SLOs, etc.)
- Asks to "generate code" for a Datadog operation
- Wants to integrate Datadog operations into their application
- Needs examples of using Datadog API clients in a specific language
Pup CLI Tool
The pup CLI is a command-line wrapper for Datadog APIs written in Rust. It provides:
- OAuth2 authentication (preferred) or API key authentication
- 28 command groups covering 33+ API domains
- JSON, YAML, and table output formats
- 200+ subcommands for comprehensive Datadog operations
Pup Authentication
# OAuth2 (preferred)
pup auth login
# API Keys (fallback)
export DD_API_KEY="your-api-key"
export DD_APP_KEY="your-app-key"
export DD_SITE="datadoghq.com"
Pup Command Structure
pup <domain> <action> [options]
pup <domain> <subgroup> <action> [options]
# Examples
pup monitors list --tags="env:prod"
pup logs search --query="status:error" --from="1h"
pup metrics query --query="avg:system.cpu.user{*}" --from="1h"
Supported Operations
Core Observability
- Metrics: Query, list, search, submit metrics
- Logs: Search and aggregate log data
- Traces: Query APM traces and spans
- Events: List and search events
- RUM: Real user monitoring data
Monitoring & Alerting
- Monitors: Full CRUD operations
- Dashboards: Create, list, get, delete
- SLOs: Service level objectives management
- Synthetics: Synthetic test management
- Downtimes: Monitor downtime management
- Notebooks: Investigation notebooks
Security & Compliance
- Security Monitoring: Rules, signals, findings
- Vulnerabilities: Security vulnerability scanning
- Static Analysis: Code security analysis
- Audit Logs: Organizational audit trail
- Data Governance: Sensitive data scanning
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.
- yesterday First seen · 552 lines · 16 tokens per session scan A a567943d0771
dd-code-generation is a skill published in the GitHub repository DataDog/pup (999 stars, last pushed 4d ago), licensed Apache-2.0. It adds 16 tokens to every session and 4,133 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 2026-08-30.
Other skills, from other repositories
PatchEvergreen Breaking Changes Analyzer
Expert skill for analyzing breaking changes, compatibility issues, and migration planning for programming libraries across multiple languages using the PatchEvergreen database.
spikard
Scaffold Spikard projects and generate code from OpenAPI, AsyncAPI, OpenRPC, GraphQL, and Protobuf schemas using the Spikard CLI or its MCP server. Use when building or updating Spikard-based apps, fixtures, test apps, or agent workflows that should prefer code generation over handwritten boilerplate.
common-task-commands
Skill "common-task-commands" from Goldziher/spikard, covering priority: critical and common task commands.
osv-ui
Security auditing skill for scanning CVE vulnerabilities across npm, Python, Go, and Rust projects using osv-ui. Opens a visual browser dashboard for human review, then applies fixes with explicit confirmation.
release-workflow
Release/publish the spikard Rust core crate and CLI end-to-end. Load when releasing or publishing spikard — cutting a new version, tagging, running gh release create, and installing the released build locally. Covers version set via Taskfile, CHANGELOG roll, the clean-tree precondition, GitHub release, local install…
query-writing
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.