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 skills add xobotyi/cc-foundry --skill youtrackgit clone --depth 1 https://github.com/xobotyi/cc-foundryWrote 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/xobotyi/cc-foundry/youtrack)<a href="https://agentmods.dev/skills/xobotyi/cc-foundry/youtrack"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/youtrack.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.03998 |
| Opus 5 | $0.00022 | $0.01999 |
| Sonnet 5 | $0.00009 | $0.00800 |
| Haiku 4.5 | $0.00004 | $0.00400 |
Grade A, and why
youtrack 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nothing about a YouTrack project is guessable. Field names, their types, their allowed values, which of them are required, which transitions a state accepts, which link types exist, what a tag does when the issue resolves — every one of these is set per project or per instance, and every one changes what a write must contain. The API reference documents the shapes; only the instance knows the values. Read the project's configuration before the first write, and read it again after changing a field that governs another.
Success is not evidence that anything changed. A command request that asks for no field projection answers 200
with an empty body by design, so the response carries nothing to check. A create can partially fail, applying the issue
and silently dropping custom-field writes. A state write on a governed field can be refused by a rule. Read the issue
back after every write, and ask for a projection wherever the endpoint offers one.
An empty result never proves absence. YouTrack filters projects and issues hidden from AI tools out of MCP responses without signalling the omission, a collection read truncates at an instance cap when no explicit limit is set, and a query naming no sort returns the most recently updated issues rather than the most relevant. A duplicate search reports what was found, never what exists.
Reach past the tool list
- The tool list is narrower than YouTrack. The MCP server built into YouTrack, at
https://<instance>/mcpsince 2025.3, has its list reshaped by the connection URL. An operation missing fromtools/listmay be filtered out rather than absent, and attachments, arbitrary commands, deletion, and link removal have no tool at all. They remain ordinary REST calls. - Let the server describe its own tools. Names, arguments, and output shapes come from
tools/listand from each tool's description, never from memory. The published documentation names the tools but does not carry their full input schemas, and a live schema has been reported rejecting a value the prose documents as valid — so the schema the server returns is the authority, not the help page. - The issue search tool returns no custom fields. Type, State, Priority, and Assignee need a per-issue read, so filtering on a field the search result omits is a two-pass operation.
- The value shape belongs to the transport, not to YouTrack. REST takes an object where a third-party MCP server may take a plain string. Read the tool's own input schema rather than carrying a shape across transports.
- Confirm the first write on an unfamiliar instance. The tool descriptions call the create and update tools writes; the security section of the same documentation set calls the predefined tools read-only. The contradiction is unresolved in the published material, so treat a first write as unproven until a read returns the new value.
- A project can watch for MCP-originated changes. An on-change workflow rule guarded by
ctx.isMcpRequestruns only for requests arriving through the server, so an edit that comes back tagged or audited is configuration, not a defect.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 227 lines · 43 tokens per session scan A 9d84ac308dec
youtrack is a skill published in the GitHub repository xobotyi/cc-foundry (20 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 3,998 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.