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 agentmods add skills/moberghr/mtk-agent-toolkit/setup-bootstrapnpx skills add moberghr/mtk-agent-toolkit --skill setup-bootstrapgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWhat 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 | $0.00030 | $0.10581 |
| Opus 5 | $0.00015 | $0.05291 |
| Sonnet 5 | $0.00006 | $0.02116 |
| Haiku 4.5 | $0.00003 | $0.01058 |
Grade D, and why
setup-bootstrap scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. Otherwise, fall back to `find ~/.claude/plugins -maxdepth 8 -name "SKILL.md" -path "*/mtk/*/context-engineering/*" -type f 2>/dev/null | sort -V | tail -1 | sed 's|/.claude/skills/context-engineering/SKILL.md||'`. If Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
> ⚠️ **Do not chain `mkdir` + `rm -rf` + `echo >` into one shell command.** Conservative permission modes reject any command that contains `rm -rf`, causing the entire chain to abort. Run each step as its own Bash call s Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL "https://raw.githubusercontent.com/moberghr/coding-guidelines/${SHA}/CodingStyle.md" -o "$OUT" How it starts
The opening of the file, as written. The whole thing — 535 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MTK Setup Bootstrap — Prepare Repository for AI-Assisted Development
MTK File Resolution
MTK skills and shared references live either in the project (local install) or the plugin cache (marketplace install). Resolve once:
- If
$MTK_HELPER_ROOTis set, prefix.claude/skills/and.claude/references/reads with it — a pinned checkout wins over every other source. - Otherwise, if
$CLAUDE_PLUGIN_ROOTis set, prefix them with that. - Otherwise, if
.claude/skills/context-engineering/SKILL.mdexists locally → project-relative paths work as-is. - Otherwise, fall back to
find ~/.claude/plugins -maxdepth 8 -name "SKILL.md" -path "*/mtk/*/context-engineering/*" -type f 2>/dev/null | sort -V | tail -1 | sed 's|/.claude/skills/context-engineering/SKILL.md||'. If empty, MTK skills are unavailable — warn the engineer and proceed withCLAUDE.mdonly.
Always project-relative (never prefixed): CLAUDE.md, .claude/tech-stack, .claude/rules/, tasks/, docs/, .claude/references/architecture-principles.md, .claude/references/pre-commit-review-list.md, .mtk/ (workflow state). Resolve skills and scripts from the same root: a split (skills from a local dev checkout, scripts from the plugin cache) risks version drift — anchor both the same way.
Companion files: several steps below defer detail to .claude/references/*.md companions, resolved via the block above. If a companion cannot be resolved at read time, stop the affected step and report the missing file path — do not reconstruct its content from memory.
You are setting up a repository for the /mtk workflows.
Your job is to detect the tech stack, audit the codebase, and generate a tailored CLAUDE.md that the implementation and review agents will use as their source of truth.
This bootstrap also prepares the repo for the shared skill layer and OpenCode routing.
Modes
Parse arguments before starting:
--preview— run detection, scan, and interview, then show the proposed CLAUDE.md + rules files diff and ask for confirmation viaAskUserQuestionbefore writing anything. Use this when the engineer wants to review before commit. Without--preview, the bootstrap writes files directly (merge mode is still the default for existing CLAUDE.md).--non-interactive— skip the post-scan interview (STEP 2.5). Use when scripting the bootstrap or when the engineer has no time for questions. Defaults to interactive.--no-verify-commands— skip STEP 3.5a's "Command verification" subsection entirely: no build/test/format commands are executed, and CLAUDE.md's Tech Stack section is written with no<!-- verified: ... -->stamp and no[UNVERIFIED]annotations. Use on a slow or sandboxed runner where executing the repo's build is undesirable. Noted in the STEP 5 report (Command verification: skipped via --no-verify-commands).
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 · 535 lines · 30 tokens per session scan D 9a512fc82cb6
setup-bootstrap is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (6 stars, last pushed 9d ago), licensed MIT. It adds 30 tokens to every session and 10,581 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (reads agent configuration directories, recursive force delete, makes network calls). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…