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 sergei-aronsen/claude-code-toolkit --skill gsd-mode-selectorgit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWrote 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/sergei-aronsen/claude-code-toolkit/gsd-mode-selector)<a href="https://agentmods.dev/skills/sergei-aronsen/claude-code-toolkit/gsd-mode-selector"><img src="https://agentmods.dev/badge/skills/sergei-aronsen/claude-code-toolkit/gsd-mode-selector.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 | $0.00056 | $0.01089 |
| Opus 5 | $0.00028 | $0.00544 |
| Sonnet 5 | $0.00011 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
gsd-mode-selector 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 7d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GSD Mode Selector
Why this skill exists
GSD has three modes with 100× cost difference. Wrong mode for task type = wasted money or insufficient quality. This skill picks the right one based on what user actually wants.
When this skill activates
- User says: "fix", "add", "change", "implement", "do", "make"
- User describes work without specifying GSD command
- Before any
/gsd-*invocation when scope unclear
Decision tree
User describes task
│
▼
Is it trivial single-fix?
(typo, 1 line, comment)
/ \
YES NO
│ │
▼ ▼
/gsd-fast Is scope < 100 LOC?
AND single-concern?
AND no security implication?
AND no breaking change?
/ \
YES NO
│ │
▼ ▼
/gsd-quick Is scope architectural?
OR multi-file?
OR security-relevant?
OR breaking change?
/ \
YES NO
│ │
▼ ▼
/gsd-plan-phase /gsd-quick
+ /council if
auth/payments
Concrete examples
| User says | Mode | Why |
|---|---|---|
| "поправь опечатку" | /gsd-fast |
Trivial, single fix |
| "добавь тест для функции X" | /gsd-quick |
Small, single concern |
| "обнови README" | /gsd-fast |
Doc update |
| "поправь баг в auth.js" | /gsd-quick (small bug) or /gsd-plan-phase (security) |
Depends |
| "добавь endpoint для users" | /gsd-quick |
Single concern, <100 LOC |
| "реализуй OAuth" | /gsd-plan-phase + /council |
Security + multi-file |
| "добавь Stripe billing" | /gsd-plan-phase + /council |
Payments + breaking |
| "переделай схему БД" | /gsd-plan-phase + /council |
Migration + breaking |
| "рефакторинг 5 файлов" | /gsd-plan-phase |
Multi-file |
| "добавь логирование" | /gsd-quick |
Single concern |
| "новая фича: notifications" | /gsd-plan-phase |
New feature scope |
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.
- 7d ago First seen · 112 lines · 56 tokens per session scan A 30d44689e141
gsd-mode-selector is a skill published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 21d ago), licensed MIT. It adds 56 tokens to every session and 1,089 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…