Borrowing it
Nothing to install: this file belongs to velesnitski/yt-mcp. 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/velesnitski/yt-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/velesnitski/yt-mcpWrote 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/velesnitski/yt-mcp/claude-md)<a href="https://agentmods.dev/instructions/velesnitski/yt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/velesnitski/yt-mcp/claude-md/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/instructions/velesnitski/yt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/velesnitski/yt-mcp/claude-md.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 | $0.01464 | $0.01464 |
| Opus 5.5 | $0.00586 | $0.00586 |
| Sonnet 5.5 | $0.00293 | $0.00293 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
yt-mcp CLAUDE.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 1mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yt-mcp
YouTrack MCP server. 84 tools across 21 modules.
Build & test
uv run python -m pytest tests/ -q # run all tests (950+)
uv run python -m pytest tests/ -v # verbose
uv pip install -e . # editable install
# Probe the LIVE API for every query shape the code builds (ADR-052).
# Asserts both directions: shapes we rely on must work, shapes the quirk
# registry calls rejected must still be rejected. Run after a Cloud
# upgrade, or when touching query construction.
YOUTRACK_URL=... YOUTRACK_TOKEN=... uv run python scripts/verify_contract.py
Architecture
src/yt_mcp/
server.py # entry point, FastMCP setup, OAuth lazy loading
client.py # YouTrackClient (httpx async, HTTP/2); maps 401/403 → YouTrackPermissionError
errors.py # UserInputError(ValueError) + YouTrackPermissionError — caller-input types, dropped from Sentry by isinstance (ADR-036)
contract.py # API-contract quirk encodings (queries + response shapes); stdlib-only, importable
commands.py # COMMAND grammar owner: bare values (no braces!), field-aware split, apply_field_commands
config.py # env var parsing, multi-instance config
resolver.py # InstanceResolver (instance name / URL auto-detection)
formatters.py # shared helpers (parse_issue_id, format_*, escape_query_value)
scoring.py # weighted scoring models for active/blocked issues
logging.py # structured JSON logging, Sentry (lazy), analytics
auth.py # OAuth 2.0 provider (lazy, only when YOUTRACK_OAUTH_URL set)
tools/
issues.py # CRUD: search, get, create, update, delete, poll_changes, count
comments.py # add, update, delete comments
attachments.py # list attachments, get download URL
projects.py # list projects, get_project_fields, agile boards
sprints.py # create, update sprint, add issues to sprint
discovery.py # list_tags, list_saved_searches, run_saved_search
history.py # issue history, rollback, work items, changes summary
bulk.py # bulk preview, execute, rollback with batch tags
translate.py # translation workflow with batch rollback
deadlines/ # deadline audit/scorecard + manager-mapping suggester (package)
pulse.py # team pulse (single + multi-board parallel) + insight flags
handoffs.py # stuck-handoff detection: cross-team transition stalls
time_report.py # monthly time reports by user (top-level workItems API)
releases.py # release calendar: in-flight + shipped + cadence ETAs
impact.py # dependency graph, deadline impact analysis
dashboard.py # scoring-based dashboards (active, blocked, team, multi-team)
monitoring.py # digest, at-risk, task creation checks, project health
templates.py # built-in issue templates
articles.py # Knowledge Base CRUD
users.py # current user, search users
__init__.py # register_all, WRITE_TOOLS set
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.
- 1mo ago Changed · +9 lines · +128 tokens per session db88e53d27a0
- 1mo ago Changed · +1 lines · +24 tokens per session 302c8da0313b
- 2mo ago First seen · 109 lines · 1,312 tokens per session scan A e3e46545c17c
yt-mcp CLAUDE.md is an instructions file published in the GitHub repository velesnitski/yt-mcp (16 stars, last pushed 8d ago), licensed MIT. It adds 1,464 tokens to every session, about $0.0059 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 2026-08-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.