Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dynatrace-oss/dynatrace-snowflake-observability-agentnpx agentmods add skills/dynatrace-oss/dynatrace-snowflake-observability-agent/plugin-developmentWrote 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/dynatrace-oss/dynatrace-snowflake-observability-agent/plugin-development)<a href="https://agentmods.dev/skills/dynatrace-oss/dynatrace-snowflake-observability-agent/plugin-development"><img src="https://agentmods.dev/badge/skills/dynatrace-oss/dynatrace-snowflake-observability-agent/plugin-development.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Privilege Escalation · line 536 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00018 | $0.07470 |
| Opus 5 | $0.00009 | $0.03735 |
| Sonnet 5 | $0.00004 | $0.01494 |
| Haiku 4.5 | $0.00002 | $0.00747 |
Grade A, and why
plugin-development 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 6d 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 — 835 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: DSOA Plugin Development
Use this skill when creating a new plugin, modifying an existing plugin, or reviewing plugin-related changes for the Dynatrace Snowflake Observability Agent (DSOA).
Lifecycle Overview
Plugin development follows a structured sequence. The first two phases are recommended but not enforced by this skill; phases 3-7 are mandatory for every plugin.
| Phase | Name | Output |
|---|---|---|
| 1 | Product planning (recommended) | Use cases, executive summary, DPO theme mapping |
| 2 | Implementation plan (recommended) | Ordered task list, reviewer-approved decisions |
| 3 | Scaffolding | Directory triad, boilerplate files |
| 4 | SQL & Python implementation | Views/procedures, Python class, config, semantics |
| 5 | Testing | Fixtures, mocked tests, all disabled_telemetry combos |
| 6 | Documentation | readme.md, config.md, USECASES.md entries, CHANGELOG + devlog file |
| 7 | Build, deploy, validate | build.sh, deploy to test-qa, verify telemetry in Dynatrace |
After plugin validation, the next step is typically dashboard/workflow creation
(see dynatrace-dashboard and dynatrace-workflow skills).
Phase 1 — Product Planning (Recommended)
Before writing code, answer these questions:
- What Snowflake problem does this plugin solve? Map to one or more DPO themes (Security, Operations, Costs, Performance, Quality).
- Which use cases does it enable? Write 3-5 concrete use cases using the
format in
docs/USECASES.md. - What Snowflake data sources does it need? Identify views, functions, commands, and their required privileges. Research latency characteristics (ACCOUNT_USAGE has ~45 min lag; INFORMATION_SCHEMA is near-real-time but per-database; SHOW commands and SYSTEM$ functions are live).
- What scheduling model fits? Single schedule (most plugins) vs dual-schedule (fast + deep, like snowpipes).
- Does it need include/exclude filtering? If it operates on user-created objects (pipes, tables, stages), yes.
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.
- 6d ago First seen · 835 lines · 18 tokens per session scan A aaa21a909ade
plugin-development is a skill published in the GitHub repository dynatrace-oss/dynatrace-snowflake-observability-agent (10 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 7,470 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 2026-09-02.
Other skills, from other repositories
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
pod-init
Initialize CocoPlus project bundle in the current directory. Creates .cocoplus/ directory structure, copies all templates, initializes AGENTS.md, project.md, flow.json, and creates the initial git commit. Run this once per project before using any other CocoPlus command.
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
pull
Distill large context files (evaluation artifacts, schema dumps, query result sets, analysis outputs) into LLM-optimized dense form or human-readable narrative (--human). Default output is machine-dense; --human produces a prose summary for stakeholder consumption.
ship
Enter the Ship phase of CocoBrew. Reads review.md approval, generates structured commit, creates semantic version tag, optionally creates PR via gh CLI, and records deployment details. Requires approved review.
spec
Enter the Spec phase of CocoBrew. Guides the developer through structured requirements capture: goal, success criteria, constraints, personas involved, data sources, and deliverables. Writes spec.md to .cocoplus/lifecycle/ and creates a git commit.