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 instructions/getsentry/warden-skills/agents-mdgit clone --depth 1 https://github.com/getsentry/warden-skillsWrote 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/instructions/getsentry/warden-skills/agents-md)<a href="https://agentmods.dev/instructions/getsentry/warden-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/getsentry/warden-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01472 | $0.01472 |
| Opus 5 | $0.00736 | $0.00736 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
warden-skills AGENTS.md 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 3d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository hosts generalized Warden skills consumed remotely by other projects.
Layout
skills/
└── wrdn-<skill-name>/
├── SKILL.md # Required. Frontmatter + analysis instructions
├── references/ # Optional. Long-form context loaded on demand
└── scripts/ # Optional. Helper scripts the skill invokes
Warden discovers skills at skills/<name>/SKILL.md automatically. No registry file or build step.
Naming
Every skill in this repo MUST be prefixed wrdn-. The prefix keeps these skills identifiable when mixed with skills from other sources in a consumer's warden.toml (e.g., wrdn-authz, wrdn-dependency-audit). The frontmatter name must match the directory exactly, prefix included.
Tooling
Install once after cloning:
pnpm install # Installs @sentry/warden (pinned in package.json)
pnpx @sentry/dotagents install # Installs authoring skills into .agents/skills/
The warden CLI is a devDependency. Run it via pnpm exec warden ... or ./node_modules/.bin/warden .... Authoring skills from getsentry/skills are declared in agents.toml; installed under .agents/skills/ (gitignored).
pnpx @sentry/dotagents add <src> <skill> # Add a new authoring skill
pnpx @sentry/dotagents list # Show what's installed
Skills
/skill-writer— Always use when creating or updating a skill inskills/. It enforces the Agent Skills spec (frontmatter, depth gates, source capture, validation).
Commit, PR, and iteration skills are installed system-wide; they aren't vendored here.
Authoring Workflow
When adding or editing a skill, start with /skill-writer. Don't write SKILL.md by hand. The skill-writer enforces the spec, captures sources, and validates the output.
Commit Attribution
AI commits MUST include:
Co-Authored-By: <model name> <[email protected]>
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.
- 3d ago First seen · 110 lines · 1,472 tokens per session scan A 7aff36dbd663
warden-skills AGENTS.md is an instructions file published in the GitHub repository getsentry/warden-skills (57 stars, last pushed 12d ago), licensed MIT. It adds 1,472 tokens to every session, about $0.0074 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 instructions, from other repositories
skills AGENTS.md
Instructions for getsentry/skills, covering agent instructions, skill structure, creating/updating skills, registration checklist and key conventions.
sentry-for-ai AGENTS.md
Instructions for getsentry/sentry-for-ai, covering agent instructions, project overview, commit attribution, repository structure and skills.
dotagents AGENTS.md
Instructions for getsentry/dotagents, covering agent instructions, package manager, what this project is, architecture and principles.
sentry-mcp AGENTS.md
AGENTS.md instructions for getsentry/sentry-mcp, covering agents.md, principles, constraints, repository structure and documentation map.
warden AGENTS.md
AGENTS.md instructions for getsentry/warden, covering agent instructions, package manager, commit attribution, architecture and key conventions.
sentry-mcp CLAUDE.md
Claude Code instructions for getsentry/sentry-mcp, a project described as: An MCP server for interacting with Sentry via LLMs.