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.
npx skills add jeremylongshore/tons-of-skills-marketplace --skill hyperflowgit 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/skills/jeremylongshore/tons-of-skills-marketplace/hyperflow)<a href="https://agentmods.dev/skills/jeremylongshore/tons-of-skills-marketplace/hyperflow"><img src="https://agentmods.dev/badge/skills/jeremylongshore/tons-of-skills-marketplace/hyperflow/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/skills/jeremylongshore/tons-of-skills-marketplace/hyperflow"><img src="https://agentmods.dev/badge/skills/jeremylongshore/tons-of-skills-marketplace/hyperflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 119 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00096 | $0.02197 |
| Opus 5 | $0.00048 | $0.01099 |
| Sonnet 5 | $0.00019 | $0.00439 |
| Haiku 4.5 | $0.00010 | $0.00220 |
Grade A, and why
hyperflow 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyperflow Doctrine (single-agent port)
Apply Hyperflow's behavioral floor in surfaces that load skills but do not provide the full Claude Code multi-agent runtime.
Runtime Adaptation
Codex, OpenCode, Antigravity, and Grok often run one foreground agent (or a host-specific subagent API). Where the full doctrine says to dispatch parallel workers under reviewers:
- Prefer the host's subagent API when it exists (Codex spawn, OpenCode Task, Grok
spawn_subagent). - Otherwise do the work yourself, one coherent batch at a time.
- Self-review each batch before moving on.
- Run a final integration self-review over the cumulative diff.
- Preserve the same autonomy, clarification, commit cadence, file-first artefact, no-attribution, and security rules.
Portable Function Router (Codex / OpenCode / Grok)
These hosts load Hyperflow as skills, not as native Claude-style slash commands. Treat these user messages as function aliases and execute the matching skill workflow inline in the current thread:
| User says | Run |
|---|---|
/hyperflow:plan, hyperflow plan, design with hyperflow, decompose with hyperflow |
plan |
/hyperflow:dispatch, hyperflow dispatch, run the hyperflow plan |
dispatch |
/hyperflow:workflow, hyperflow workflow, run a workflow |
workflow |
/hyperflow:trace, hyperflow trace, debug with hyperflow |
trace |
/hyperflow:audit, hyperflow audit, review with hyperflow |
audit |
/hyperflow:deploy, hyperflow deploy, ship with hyperflow |
deploy |
/hyperflow:cache, hyperflow cache |
cache |
/hyperflow:status, hyperflow status |
status |
/hyperflow:sticky, hyperflow sticky |
sticky |
/hyperflow:bridge, hyperflow bridge |
bridge |
/hyperflow:flush, hyperflow flush |
flush |
/hyperflow:background, hyperflow background |
background |
/hyperflow:scaffold, hyperflow scaffold |
scaffold |
Do not answer that /hyperflow:* is an unknown command on these surfaces. Strip the alias, load the matching skills/<name>/SKILL.md, and follow its workflow. If that workflow says to use unavailable Claude Code tools (Agent, Skill, or AskUserQuestion), emulate them: do worker/reviewer steps inline with visible labels, continue chained skills inline, and use the interaction fallback below when a structured question UI is missing.
What ships with it
36 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.
- adaptive-brainstorming.md 13 KB
- artefact-format.md 14 KB
- background-agents.md 13 KB
- brainstorming-advanced.md 6.1 KB
- consultation.md 4.7 KB
- design-system.md 7.4 KB
- doctrine-extensions.md 9.2 KB
- DOCTRINE.md 97 KB
- escalation.md 17 KB
- failure-recovery.md 7.6 KB
- feature-phases.md 7.0 KB
- flow-profiles.md 21 KB
- git-workflow.md 5.9 KB
- latency-patterns.md 21 KB
- memory-system.md 15 KB
- mobile.md 4.4 KB
- model-config.md 5.0 KB
- motion.md 7.4 KB
- output-style.md 8.7 KB
- personas-A.md 37 KB
- personas-B.md 26 KB
- project-analysis.md 8.3 KB
- quality-gates.md 2.0 KB
- review-levels.md 4.4 KB
- reviewer-prompt-batched.md 8.6 KB
- reviewer-prompt.md 4.4 KB
- security.md 4.6 KB
- session-handoff.md 7.4 KB
- session-memory.md 1.3 KB
- task-templates.md 2.8 KB
- task-tracking.md 6.7 KB
- task-triage.md 17 KB
- VERSION 6 B
- web-research.md 4.5 KB
- worker-prompt-lean.md 5.9 KB
- worker-prompt.md 18 KB
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 · 139 lines · 96 tokens per session scan A fa9efca886ce
hyperflow is a skill published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 2,197 once invoked, about $0.0005 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 skills, from other repositories
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
loop-graph
Compile one durable loop-graph run into executor, ledger, directives, ops, and supervisor artifacts under a dated .longgraph directory, then present copy-ready host prompts. Use directly for a custom multi-round shape with gated milestones, independent audit, cross-host execution, or durable state; focused sibling…
agent-team-handoff
A workflow for coordinating several AI assistants or agents on one project. It uses shared handoff files to record the current task, roles, decisions, progress, next steps, and proof of completion.
longgraph
Route and author durable long-horizon loop-graph runs. Use for multi-round work needing durable state, gated milestones, owner boundaries, host switching, or independent audit. Route code cleanup to /loop-converge, feature requirements to /loop-deliver, and evidence-backed solution comparison to /loop-research; use…
loop-converge
Author and optionally direct-launch a two-node loop-graph run whose North Star is code convergence — delete unused code, merge duplicates, reuse, slim. Use when the user invokes /loop-converge, or asks to loop on dead code, duplication, unused exports, DRY cleanup, or merging twin implementations. Starts the owner…
loop-deliver
Author and optionally direct-launch a two-node loop-graph run for implementing a product or engineering requirement through verified vertical slices. Use when a requested feature, integration, migration, or behavior change needs multiple rounds, durable acceptance proof, and independent audit. Not for code cleanup…