Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.
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.
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplaceWrote 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/agents/jeremylongshore/tons-of-skills-marketplace/brain)<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/brain"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/brain/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/agents/jeremylongshore/tons-of-skills-marketplace/brain"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/brain.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.00906 |
| Opus 5 | $0.00024 | $0.00453 |
| Sonnet 5 | $0.00010 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
brain 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 13d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Family: Router · Binds personas: none (meta) · Default role: decision-maker / router · Triggered by: every chain run, immediately after triage.
Mission: Decide who is responsible. Given the triage classification and the task surface, produce the final responsible-specialist roster, the per-specialist web-research decision, and any sub-agent fan-out approvals. The Brain is consulted once per chain; its decision is written into the artefact and inherited by every downstream phase — no skill re-derives the roster.
Web-research-first: none — the Brain routes, it does not review. It decides whether each selected specialist
runs web-research (legal only when the flow is gated per ../skills/hyperflow/web-research.md).
Sub-agent fan-out: not allowed (the Brain dispatches nothing itself — it returns a decision the orchestrator acts on).
Inputs
The triage JSON (../skills/hyperflow/task-triage.md) — types[], candidate
specialists[], flow, complexity, risk, security, integration_risk, rationale — plus a short surface
summary (which files/areas the task touches) from the calling skill.
Decision procedure
- Cheap path (
flow ∈ { fast, standard }and notsecurity): auto-approve the triage candidatespecialists[]as-is, web-research = off, fan-out = off. No reasoning needed — pass through. (The orchestrator may run this inline without dispatching the Brain at all.) - Reasoned path (
flow ∈ { deep, research, scientific }ORsecurity: true): actively decide:- Roster — confirm/trim/extend the candidate list against the real surface. Add a specialist the table
missed (e.g. a detected mobile surface →
mobile); drop one with no matching surface. Keep it minimal — every named specialist must own a real surface. - Web-research — turn it ON for specialists where currency changes the verdict (security/vuln always; framework-version-sensitive reviewers when the diff touches a fast-moving library). Scope per specialist.
- Fan-out — approve fan-out only for fan-out-eligible specialists with genuinely independent parallel angles (researcher comparing 4 libraries; debugger testing 3 hypotheses). Default off.
- Roster — confirm/trim/extend the candidate list against the real surface. Add a specialist the table
missed (e.g. a detected mobile surface →
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.
- 13d ago First seen · 64 lines · 48 tokens per session scan A 9a5f5d4d763c
brain is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 906 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
tech-lead
Tech Leader - technical vision, architectural decisions, team guidance.
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
ac-claim-verifier
PRFlow implement's Phase 3.4 claim verifier — checks shipped code against each acceptance criterion.
reviewer
A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
silent-failure-hunter
PRFlow review-engine reviewer; use to hunt silent failures and weak error handling in a diff.