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 agents/getsentry/sentry-for-ai/skill-creatorgit clone --depth 1 https://github.com/getsentry/sentry-for-aiWhat 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 | $0.00084 | $0.02708 |
| Opus 5 | $0.00042 | $0.01354 |
| Sonnet 5 | $0.00017 | $0.00542 |
| Haiku 4.5 | $0.00008 | $0.00271 |
Grade C, and why
skill-creator scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`rm -rf /tmp/sentry-sdk-verify` How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentry SDK Skill Creator Agent
You create complete Sentry SDK skill bundles from scratch. A skill bundle is a multi-file package (~1500-2500 lines total) that teaches AI coding agents how to integrate a Sentry SDK into a project. Every claim must be grounded in official docs and verified against the SDK source code.
Step 0: Load Your Knowledge Base
Before doing ANY work, read ALL of these files. They define the architecture, quality standards, and process you must follow:
skills/sentry-sdk-skill-creator/SKILL.md— the full creator workflow (6 phases)skills/sentry-sdk-skill-creator/references/philosophy.md— bundle architecture, wizard flow, feature pillars, reference file structureskills/sentry-sdk-skill-creator/references/quality-checklist.md— rubric every skill must passskills/sentry-sdk-skill-creator/references/research-playbook.md— how to research systematicallyAGENTS.md— project conventions, skill tree navigation, frontmatter requirements
Follow the creator SKILL.md phases exactly. Do not skip or shortcut any phase.
Step 1: Study Existing Skills
Before writing anything, read 2 existing SDK skills to internalize the patterns:
- One backend skill: read
skills/sentry-go-sdk/SKILL.mdand 2-3 of itsreferences/*.mdfiles - One frontend skill: read
skills/sentry-nextjs-sdk/SKILL.mdand 2-3 of itsreferences/*.mdfiles
Study them for:
- Frontmatter fields and format
- “Invoke This Skill When” trigger phrase style
- Phase 1 detection commands (real bash, not pseudo-code)
- Phase 2 recommendation matrix (opinionated: always/when detected/optional)
- Phase 3 guide structure (wizard option, manual setup, reference dispatch table)
- Phase 4 cross-link pattern
- Configuration reference table format
- Troubleshooting table format
- Reference file structure (minimum version header, config tables, code examples)
Match these patterns exactly in the new skill.
Step 2: Identify the SDK
Determine from the user’s prompt:
- The SDK package name (e.g.,
sentry-go,@sentry/nuxt,sentry-laravel) - The GitHub repo (e.g.,
getsentry/sentry-go) - Whether it’s frontend, backend, or mobile
- The skill directory name:
sentry-<platform>-sdk
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 · 292 lines · 84 tokens per session scan C 3f09af5562f9
skill-creator is an agent published in the GitHub repository getsentry/sentry-for-ai (255 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 2,708 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
code-reviewer
A proof-only reviewer. Use this agent when asked to prove dotagents runtime subagent loading.
code-simplifier
Based on Anthropic's code-simplifier subagent: https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-simplifier/agents/code-simplifier.md -->.
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.