Borrowing it
Nothing to install: this file belongs to tortastudios/sentry-instrumentation. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tortastudios/sentry-instrumentation/main/AGENTS.mdgit clone --depth 1 https://github.com/tortastudios/sentry-instrumentationWrote 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/tortastudios/sentry-instrumentation/agents-md)<a href="https://agentmods.dev/instructions/tortastudios/sentry-instrumentation/agents-md"><img src="https://agentmods.dev/badge/instructions/tortastudios/sentry-instrumentation/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 5.1 | $0.01038 | $0.01038 |
| Opus 5 | $0.00519 | $0.00519 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
sentry-instrumentation 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 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents guide — sentry-instrumentation
What this repo is
sentry-instrumentation is an Anthropic-format skill: a set of rules,
references, and drop-in code patterns that teach AI coding agents how to
add Sentry instrumentation the right way — both metrics (counter /
gauge / distribution, duration, failure, resource) and tracing (the
gen_ai.* spans for AI agent conversations). The canonical reference
ships in Python under examples/python/, but the patterns are
language-neutral and port to TypeScript, Go, Ruby, etc. The skill is
production-tested at Torta Studios.
This is not an application. There is nothing to run from this repo — it is installed into consumer projects so that an AI agent working in those projects reads its rules.
This repo has no "skill registry"
There is no cross-agent "skill registry file" standard. Each supported agent discovers skills its own way:
| Agent | Discovery file |
|---|---|
| Claude Code | SKILL.md YAML frontmatter under ~/.claude/skills/ or .claude/skills/ |
| Claude.ai (web) | SKILL.md YAML frontmatter uploaded via Settings → Skills |
| Codex | AGENTS.md at project root |
| Cursor | .cursor/rules/*.mdc |
| Aider | CONVENTIONS.md (or any file passed via --read) |
| Continue | .continuerules |
| Windsurf | .windsurfrules |
The install shape for each agent lives under adapters/<agent>.md. The
matrix is in adapters/README.md.
If you're a Codex agent asked to install this skill
One command, from inside the cloned skill repo:
scripts/install.sh --agent=codex --project=/path/to/consumer/project
That appends the Skill-enable block below into the consumer project's
AGENTS.md, bracketed by marker comments so re-runs update in place.
If you prefer to do it by hand, copy the block below into the consumer
project's AGENTS.md, and adjust the paths to point at the cloned skill
on disk.
Skill-enable block (copy into consumer AGENTS.md)
<!-- BEGIN sentry-instrumentation -->
## Sentry instrumentation
This project uses the `sentry-instrumentation` skill. When writing code
that emits a Sentry metric, measures duration, counts failures, wraps a
workflow step, adds a retry or fallback path, or instruments an AI agent
/ LLM call / tool call / conversation:
1. Read `<path-to-skill>/SKILL.md`.
2. Follow its decision rules and surface patterns.
3. For deeper rules (tagging, cost model, lifecycle, AI agent
conversations), open the relevant file under
`<path-to-skill>/references/`.
4. Use `<path-to-skill>/examples/python/` as the canonical drop-in
reference.
Never hand-roll emissions — use the surface patterns (middleware,
decorator, base class). Never pass a raw string to an emit helper. For
AI agents, use `gen_ai.*` spans and set `gen_ai.conversation.id` per
turn — keep the conversation id and message bodies on span attributes,
never on a metric tag.
<!-- END sentry-instrumentation -->
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 · 101 lines · 1,038 tokens per session scan A ced0403d24e6
sentry-instrumentation AGENTS.md is an instructions file published in the GitHub repository tortastudios/sentry-instrumentation (24 stars, last pushed 2mo ago), licensed MIT. It adds 1,038 tokens to every session, about $0.0052 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.