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/mtknpx skills add moberghr/mtk-agent-toolkit --skill mtkgit clone --depth 1 https://github.com/moberghr/mtk-agent-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/moberghr/mtk-agent-toolkit/mtk)<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/mtk"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/mtk.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 | $0.00017 | $0.04509 |
| Opus 5 | $0.00009 | $0.02254 |
| Sonnet 5 | $0.00003 | $0.00902 |
| Haiku 4.5 | $0.00002 | $0.00451 |
Grade A, and why
mtk 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 5d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MTK — Unified Entry Point
You are a router. Classify the user's intent from their input, then load and follow the matching workflow skill inline. Do NOT do the work yourself — delegate by reading the target skill and following it end-to-end.
Routing Decision Graph
This graph is the canonical decision flow. The Route Table below is the lookup; this graph is the order. Walk the diamonds top to bottom; first match wins.
digraph mtk_routing {
rankdir=TB;
node [shape=box, style=rounded, fontname="Helvetica"];
edge [fontname="Helvetica", fontsize=10];
start [label="user input"];
empty [label="empty / help?", shape=diamond];
help [label="print help", style="rounded,filled", fillcolor="#e8f0ff"];
bfesc [label="contains\n'escalated from fix (batch)'?", shape=diamond];
esc [label="contains 'escalated from fix'\nor 'escalated from batch-fix'?", shape=diamond];
setup [label="setup / bootstrap /\naudit / init / first time?", shape=diamond];
redirect [label="redirect: /mtk-setup", style="rounded,filled", fillcolor="#e8f0ff"];
rev [label="review / commit /\nstaged / pre-commit?", shape=diamond];
pcr [label="pre-commit-review", style="rounded,filled", fillcolor="#e0f0e0"];
rhlth [label="repo-health / readiness /\nscorecard / ai-ready?", shape=diamond];
rh [label="repo-health", style="rounded,filled", fillcolor="#e0f0e0"];
prm [label="mine prs /\npr mining?", shape=diamond];
prmine [label="pr-review-mining", style="rounded,filled", fillcolor="#e0f0e0"];
doc [label="doctor / broken /\nintegrity / install health?", shape=diamond];
mdoc [label="mtk-doctor", style="rounded,filled", fillcolor="#e0f0e0"];
hlth [label="usage / stats /\nanalytics / adoption?", shape=diamond];
th [label="toolkit-health", style="rounded,filled", fillcolor="#e0f0e0"];
rsch [label="research / best practice /\ncurrent way / latest version?", shape=diamond];
rc [label="research-context", style="rounded,filled", fillcolor="#e0f0e0"];
fixv [label="fix / bug / broken /\nerror / typo / failing?", shape=diamond];
feat [label="add / create / build /\nfeature / implement / new?", shape=diamond];
ambig [label="ALSO matches feature\n(e.g. 'fix the auth feature')?", shape=diamond];
ask [label="ask ONE Q:\nsmall fix (1-3 files),\nbatch of small independent fixes,\nor larger feature?", style="rounded,filled", fillcolor="#fff8d0"];
bfixv [label="multiple independent small\nfixes / corrective batch,\nno new contract?", shape=diamond];
fix [label="fix", style="rounded,filled", fillcolor="#e0f0e0"];
bfixkw [label="explicit batch-fix keywords?\n('batch fix' / 'apply review\nfindings' / 'corrective batch')", shape=diamond];
bfix [label="batch-fix", style="rounded,filled", fillcolor="#e0f0e0"];
impl [label="implement", style="rounded,filled", fillcolor="#e0f0e0"];
stat [label="status / report /\nwhat's loaded / diagnostic?", shape=diamond];
cr [label="context-report", style="rounded,filled", fillcolor="#e0f0e0"];
cmd [label="audit claude.md /\nclaude.md stale?", shape=diamond];
cma [label="claude-md-audit", style="rounded,filled", fillcolor="#e0f0e0"];
cmc [label="capture session\nlearnings to claude.md?", shape=diamond];
cmcap [label="claude-md-capture", style="rounded,filled", fillcolor="#e0f0e0"];
prom [label="promote / share\na lesson?", shape=diamond];
plsn [label="promote-lesson", style="rounded,filled", fillcolor="#e0f0e0"];
ho [label="hand off / save state /\nsnapshot session?", shape=diamond];
hoff [label="handoff", style="rounded,filled", fillcolor="#e0f0e0"];
start -> empty;
empty -> help [label="yes"];
empty -> bfesc [label="no"];
bfesc -> bfix [label="yes (internal marker)"];
bfesc -> esc [label="no"];
esc -> impl [label="yes (internal marker)"];
esc -> bfixkw [label="no"];
bfixkw -> bfix [label="yes"];
bfixkw -> rev [label="no"];
rev -> pcr [label="yes"];
rev -> rhlth [label="no"];
rhlth -> rh [label="yes"];
rhlth -> prm [label="no"];
prm -> prmine [label="yes"];
prm -> doc [label="no"];
doc -> mdoc [label="yes"];
doc -> hlth [label="no"];
hlth -> th [label="yes"];
hlth -> rsch [label="no"];
rsch -> rc [label="yes"];
rsch -> fixv [label="no"];
fixv -> ambig [label="yes"];
ambig -> ask [label="yes"];
ambig -> fix [label="no"];
ask -> fix [label="user: small fix"];
ask -> bfix [label="user: batch of small fixes"];
ask -> impl [label="user: larger feature"];
fixv -> bfixv [label="no"];
bfixv -> bfix [label="yes"];
bfixv -> feat [label="no"];
feat -> impl [label="yes"];
feat -> stat [label="no"];
stat -> cr [label="yes"];
stat -> cmd [label="no"];
cmd -> cma [label="yes"];
cmd -> cmc [label="no"];
cmc -> cmcap [label="yes"];
cmc -> prom [label="no"];
prom -> plsn [label="yes"];
prom -> ho [label="no"];
ho -> hoff [label="yes"];
ho -> setup [label="no"];
setup -> redirect [label="yes"];
setup -> help [label="no match → help"];
}
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.
- 5d ago First seen · 225 lines · 17 tokens per session scan A 40bf91468040
mtk is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 4,509 once invoked, about $0.0001 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-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…