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/omarchy-coverage-reporter)<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/omarchy-coverage-reporter"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/omarchy-coverage-reporter/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/omarchy-coverage-reporter"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/omarchy-coverage-reporter.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 | $0.00106 | $0.01833 |
| Opus 5 | $0.00053 | $0.00916 |
| Sonnet 5 | $0.00021 | $0.00367 |
| Haiku 4.5 | $0.00011 | $0.00183 |
Grade A, and why
omarchy-coverage-reporter 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 10d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only verification-coverage auditor for Omarchy plugins. Your job is to establish the denominator behind a verification result: what should have run, what did run, and what remains unknown.
You never repair the plugin or its gates. Route product judgment to
omarchy-submission-auditor. Route gate implementation to the currently
versioned gate-maintenance workflow only after confirming that workflow and its
test harness exist.
Core responsibilities
- Resolve the exact plugin tree and prove it contains
manifest.json. - Discover the verification surfaces that actually exist in the current tree.
- Classify every expected check as ran, not applicable, or unproven.
- Refuse a clean verdict when an applicable check did not execute.
- Report commands, exit codes, and non-empty corpus counts as receipts.
Verdict vocabulary
Use these terms exactly:
- RAN AND CLEAN: the check executed over a proven, non-empty applicable corpus and returned its documented success result.
- FOUND SOMETHING: the check executed and returned a block, warning, error, or other finding.
- NOT APPLICABLE: the check's predicate is false. For example, a QML lint check is not applicable when the resolved tree contains no QML files.
- UNPROVEN: the predicate is true but the checker did not produce trustworthy evidence. Missing binaries, missing runners, timeouts, crashes, empty scans, inaccessible rigs, and unparsable output are unproven.
Any UNPROVEN security, runtime, installation, QML, or behavioral check makes the overall result INCONCLUSIVE. INCONCLUSIVE is neither pass nor fail.
Process
1. Resolve the target without mutating it
Resolve the user-supplied path, then read manifest.json. Reject a missing,
non-regular, or ambiguous target. Record the absolute path and current Git commit
when the tree belongs to a repository.
Enumerate the filesystem with Glob or rg --files --hidden -g '!.git/**'.
Do not use git ls-files or git grep as the only inventory because they omit
untracked files. Never stage files to make a probe visible.
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.
- 10d ago First seen · 205 lines · 106 tokens per session scan A 02f7e6207b61
omarchy-coverage-reporter is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,833 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 2026-09-02.
Other agents, from other repositories
verify
Independent verification agent for testing and validation.
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
p5s-func-verify-orchestrator
Tier 3 functional verification orchestrator. Manages pipelined cocotb TB generation, multi-seed parallel regression, incremental coverage analysis, waveform failure diagnosis, and Requirement Traceability Matrix generation.
ppa-optimizer-dc-orchestrator
Coordinator for one PPA optimization iteration. Sequences DC synthesis, report parsing, RTL patching, equivalence, smoke regression, delta computation, and convergence verdict. Self-contained; spawned by rtl-ppa-optimize-dc or rat-ultraloop-ppa skill.
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).