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 DeevsDeevs/agent-system --skill datadog-pupgit clone --depth 1 https://github.com/DeevsDeevs/agent-systemWrote 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/deevsdeevs/agent-system/datadog-pup)<a href="https://agentmods.dev/skills/deevsdeevs/agent-system/datadog-pup"><img src="https://agentmods.dev/badge/skills/deevsdeevs/agent-system/datadog-pup/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/deevsdeevs/agent-system/datadog-pup"><img src="https://agentmods.dev/badge/skills/deevsdeevs/agent-system/datadog-pup.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 | $0.00041 | $0.01385 |
| Opus 5.5 | $0.00016 | $0.00554 |
| Sonnet 5.5 | $0.00008 | $0.00277 |
| Haiku 4.5 | $0.00004 | $0.00138 |
Grade A, and why
datadog-pup 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Datadog via Pup
Pup is broad and self-describing; prefer live command discovery over memorized flags.
First moves
which pup && pup --version && pup auth status. This user's org is ondatadoghq.eu— exportDD_SITE=datadoghq.eufor the session. If auth is missing/expired, ask the user to runpup auth loginor provide the rightDD_SITE. Do not loop on 401/403.- Discover before guessing:
pup agent schema --compact(command map),pup agent guide,pup <domain> --help.FORCE_AGENT_MODE=1turns help into JSON — never use it for writes without--read-only; agent mode may auto-approve prompts. - Prefer
--output=json,--read-only, explicit--from, and small limits:
DD_SITE=datadoghq.eu pup --read-only logs search --query="status:error" --from="1h" --limit=20 --output=json
Safety rules
- Treat Datadog as production data. Default to read-only; writes (create/update/delete, downtimes, debugger probes, workflow runs, key/user/config changes) need explicit confirmation with the exact command or JSON body shown first.
- Use API-side filters/aggregation; never fetch huge datasets to post-process locally. Always pass
--from; start narrow (15m–1h, low limits) and widen only with a reason. - Redact secrets, tokens, emails, user IDs, and sensitive attributes unless explicitly needed. Preserve IDs and links so findings are auditable.
- 401/403: stop, report auth/scope issue, suggest
pup auth refresh/loginor key scopes. 429: back off and narrow.
Common read workflows
Logs — count first, then sample. Query syntax: status:error, service:api, env:prod, @http.status_code:[500 TO 599], quoted phrases, AND/OR, negation:
pup --read-only logs aggregate --query="status:error env:prod" --from="1h" --compute="count" --group-by="service" --output=json
pup --read-only logs search --query="status:error env:prod service:<svc>" --from="1h" --limit=20 --output=json
Metrics — shape <aggregation>:<metric>{<scope>} by {<group>}:
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 · 83 lines · 41 tokens per session scan A 410cba32b59f
datadog-pup is a skill published in the GitHub repository DeevsDeevs/agent-system (41 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 1,385 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 2026-11-05.
datadog-pup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| datadog-pupDeevsDeevs/agent-system | Skill | 41 | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| cdf-anomalygenNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| deepstream-sopNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 219 | Claude Code |
| jetson-diagnosticNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code, Codex |
| parabricksNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 32 | Claude Code, Codex |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |