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 monte-carlo-data/mc-agent-toolkit --skill toolkit-skill-authorgit clone --depth 1 https://github.com/monte-carlo-data/mc-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/monte-carlo-data/mc-agent-toolkit/toolkit-skill-author)<a href="https://agentmods.dev/skills/monte-carlo-data/mc-agent-toolkit/toolkit-skill-author"><img src="https://agentmods.dev/badge/skills/monte-carlo-data/mc-agent-toolkit/toolkit-skill-author.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 | $0.02227 |
| Opus 5 | $0.00028 | $0.01113 |
| Sonnet 5 | $0.00011 | $0.00445 |
| Haiku 4.5 | $0.00006 | $0.00223 |
Grade C, and why
toolkit-skill-author scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
!rm -rf skills/<peer>/evals/ skills/<peer>-workspace/ How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
toolkit-skill-author
Pre-load
!test -f CONTRIBUTING.md || (echo "CONTRIBUTING.md missing — run from repo root." && exit 1)
Verify skill-creator is callable in this session. Scan the available-skills list for a skill named skill-creator (bare or namespaced, e.g. skill-creator:skill-creator). If absent, abort with exactly this message:
skill-creatorplugin is required. Run/plugin install skill-creator@claude-plugins-official, enable it, then restart this session and re-run/toolkit-skill-author.
Do not fall back to manually scaffolding SKILL.md — the handoff is core to the workflow.
Load authoritative context:
!cat CONTRIBUTING.md
!bash .claude/skills/toolkit-skill-author/scripts/find-peers.sh skills
- @.claude/skills/toolkit-skill-author/references/decision-rules.md
- @.claude/skills/toolkit-skill-author/references/handoff-preamble.md
- @.claude/skills/toolkit-skill-author/references/registration-checklist.md
Phase 0 — Parse intent and apply gates
From the contributor's initial prompt, extract (without asking yet):
target_name— did they name a specific skill (e.g., "extendmonitoring-advisor", "create a skill calledfoo-bar")?action—extend,new, orunknown.bucket— did they state a capability bucket?
Apply the gates below before any survey question. Each gate halts when it fires.
Gate A — Forbidden bucket
If bucket is Agent-routing (or a synonym like "agent routing", "routing skill"), refuse:
Agent-routing skills are owned by the toolkit core team per
CONTRIBUTING § Capability buckets— not authored via/toolkit-skill-author. Halting.
Do not proceed. If bucket is unstated, this gate re-applies after Q1.
Gate B — Name collision (new-skill intent)
If action is new and target_name is given, lowercase both target_name and each existing skill directory name, then check:
- Exact match (equal strings): refuse with "
<target_name>already exists inskills/. Pick a different name, or switch to extend." Do not proceed. - Near match. Split both names on
-into token lists. Fire if either (a) the two lists share any token, or (b) any token in one list is a substring of any token in the other list. Example:monitor-advisor↔monitoring-advisorfires via (a) sharedadvisorand (b)monitor⊂monitoring. When fired, surface the overlap and ask: "<target_name>overlaps with existing<existing>. Did you mean to extend<existing>, or proceed with a new name?" Wait for an answer before continuing.
What ships with it
9 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.
- README.md 5.7 KB
- references/decision-rules.md 3.2 KB
- references/handoff-preamble.md 3.4 KB
- references/registration-checklist.md 3.0 KB
- scripts/find-peers.sh 1020 B runs code
- scripts/lint-skill.py 5.6 KB runs code
- scripts/tests/find-peers.bats 1.2 KB
- scripts/tests/lint-skill.bats 5.9 KB
- scripts/tests/smoke-test.sh 2.4 KB runs code
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.
- 8d ago First seen · 175 lines · 56 tokens per session scan C 0b2e4430d1a9
toolkit-skill-author is a skill published in the GitHub repository monte-carlo-data/mc-agent-toolkit (91 stars, last pushed 14d ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,227 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
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.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…