JetBrains/thinkrail is a desktop and mobile client that embeds the pi coding agent inside an interface for editing code and managing development workspaces. Developers use it to work on Git repositories through separate worktrees, a Monaco editor, terminals, Git views, specifications, and concurrent agent sessions. The catalogue entries are skills and instructions for its agent-based development workflow.
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 JetBrains/thinkrail --skill writing-specsgit clone --depth 1 https://github.com/JetBrains/thinkrailWrote 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/jetbrains/thinkrail/writing-specs)<a href="https://agentmods.dev/skills/jetbrains/thinkrail/writing-specs"><img src="https://agentmods.dev/badge/skills/jetbrains/thinkrail/writing-specs/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/skills/jetbrains/thinkrail/writing-specs"><img src="https://agentmods.dev/badge/skills/jetbrains/thinkrail/writing-specs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00686 |
| Opus 5.5 | $0.00024 | $0.00274 |
| Sonnet 5.5 | $0.00012 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
writing-specs 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 23d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Specs
The workflow family's shared bar for every spec a workflow produces: short, honest, on-rails.
Process skills name this concept at the steps that draft or revise specs; what to draft and when
stays with the referencing skill. Graph mechanics — frontmatter, link kinds, the spec_* tools — are
the spec-graph skill's ground; this concept carries the quality bar the family holds on top of them,
and is where the family's rules for specs and the spec graph accrue.
Short
- Small enough to read in one sitting. Target signal, not completeness.
- Explain intent, not inventory: what the thing is for, what it owns, where its boundary runs — never a file listing or a restatement of the code.
Honest
- Only settled content appears. Never pad with
[TBD]or placeholder sections — a section that hasn't been settled simply doesn't exist yet. - Anything inferred rather than confirmed is marked unconfirmed, inline, where it stands.
- New and inferred specs are
status: draftuntil the user has reviewed them — the flip out ofdraftfollows the user's review, never the drafting agent's own judgment. A reviewed durable spec goesactive, neverdone: it stays in force and evolves with the project.
On-rails
- High-signal enough that a future agent (or human) lands on the decisions without re-deriving them.
- The spec is the only home for rationale: decisions, invariants, trade-offs, and bug post-mortems are recorded here, never as code comments — a rationale paragraph found in code is content to promote into the owning spec, leaving at most a one-line pointer where misediting would silently break something.
- Say each thing once: link by
idinstead of restating; the dependency edges between sibling modules live in the parent's spec, not in each leaf. - One spec per genuine boundary — not per directory, not per file.
The goal doc describes the product, not a plan
goal-and-requirements is the living record of what the product is and why: its goal, problem,
audience, capabilities, and non-goals, plus any durable principles.
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.
- 23d ago Changed · +15 lines 3d5ab7144d0d
- 1mo ago First seen · 38 lines · 59 tokens per session scan A 2b827c405fb8
writing-specs is a skill published in the GitHub repository JetBrains/thinkrail (988 stars, last pushed today), licensed Apache-2.0. It adds 59 tokens to every session and 686 once invoked, about $0.0002 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 skills, from other repositories
nexent-daily-test
A procedure for running Nexent daily, full-layer tests on a self-hosted Ubuntu machine. Nexent is tested across separate layers such as unit, service, AI runtime, and browser journeys, with results and evidence kept locally.
skillpack-creator
Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with skillpack.json, local skills under skills/, starter prompts, start scripts, and an optional zip package.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
bello-config-advisor
Inspect a coding task, repository, and user preferences, then recommend one concrete Bello configuration and decide whether a separate planning pass should precede execution. Use when the user asks to choose or optimize a Bello setup before a run, from Codex, Claude Code, or another host. Do not use merely to monitor…
vigilante-create-issue
Help a human author write an implementation-ready GitHub issue that Vigilante can execute reliably.
rn-device-control
This skill should be used when the user asks to "control the simulator", "take a screenshot", "boot the emulator", "install the app", "read UI hierarchy", "manage device state", "open a deep link", "grant permissions", "stream native logs", "disable animations", "change device locale", or needs guidance on xcrun…