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/filip-podstavec/claude-leverage/stack-checknpx skills add Filip-Podstavec/claude-leverage --skill stack-checkgit clone --depth 1 https://github.com/Filip-Podstavec/claude-leverageWrote 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/filip-podstavec/claude-leverage/stack-check)<a href="https://agentmods.dev/skills/filip-podstavec/claude-leverage/stack-check"><img src="https://agentmods.dev/badge/skills/filip-podstavec/claude-leverage/stack-check.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 | $0.00094 | $0.04006 |
| Opus 5 | $0.00047 | $0.02003 |
| Sonnet 5 | $0.00019 | $0.00801 |
| Haiku 4.5 | $0.00009 | $0.00401 |
Grade A, and why
stack-check 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/stack-check
What it does
Walks stack.toml, queries each declared dependency's installed version,
optionally fetches the latest available version, and reports a Markdown
table:
# Stack check — <YYYY-MM-DD>
| Tool | Installed | Required | Status | Update |
|------|-----------|----------|--------|--------|
| claude (Claude Code) | 2.1.89 | ≥2.1.0 | ok | — |
| codex (Codex CLI) | 0.39.0 | ≥0.40.0 | **outdated** | npm i -g @openai/codex |
| claude-leverage (this plugin) | 1.0.0 | latest 1.0.1 | **outdated** | /plugin update claude-leverage |
| git | 2.45.0 | ≥2.40.0 | ok | — |
| rg | 14.0.3 | ≥13.0.0 | ok | — |
| jq | (not found) | ≥1.6 (optional) | missing | brew install jq |
| python | 3.12.1 | ≥3.10 | ok | — |
| mmdc | (not found) | ≥10.0.0 (optional) | missing | npm i -g @mermaid-js/mermaid-cli |
| node | 20.10.0 | ≥20.0.0 | ok | — |
| shellcheck | (not found) | ≥0.8.0 (optional) | missing | brew install shellcheck |
On successful completion (no errors thrown), updates
~/.local/state/claude-leverage/.last-stack-check (or
~/.claude/claude-leverage/.last-stack-check if XDG state dir is
unavailable) with the current epoch time so the SessionStart hook stays
quiet for the next N days.
Workflow
-
Load
stack.toml. From the plugin install dir ($CLAUDE_PLUGIN_ROOT/stack.toml) or, if running standalone, from the repo root. If neither exists, STOP and report. -
For each
[[host.tool]]and[[deps.tool]]:- Run
check_cmd. Capture stdout+stderr. - Parse the version with a simple regex (
(\d+\.\d+(\.\d+)?)— accept "X.Y" and "X.Y.Z" both). If parse fails or command not found, mark "missing" (and "outdated" ifoptional = false). - Compare against
min_versionusing a tuple compare (split on.). - Mark:
ok|outdated|missing|unknown (parse failed). - Resolve update hint per-OS: detect platform via
uname -s(or PowerShell$env:OS/$IsWindows). Preferupdate_hint_macos/update_hint_linux/update_hint_windowswhen present and the platform matches; otherwise fall back to the genericupdate_hintfield. This is what stack.tomlmanifest_version = 2introduced.
- Run
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 · 320 lines · 94 tokens per session scan A c71d1ba12218
stack-check is a skill published in the GitHub repository Filip-Podstavec/claude-leverage (68 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 4,006 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
codex-pair-resume
Resume codex-pair for this project after a previous pause. Removes .codex-pair/state/paused and clears failure state. Review resumes on the next supported file edit; missing state is a no-op.
generate-tests
Generate unit tests for a .NET service following the coverage-kit conventions. Use when the user asks to 'generate tests', 'backfill tests', 'characterize this service', or 'add tests for' a target after coverage-init has run. Operates in characterization mode (freeze current behavior for existing code) or spec mode…
opik
This skill should be used when the user needs to add Opik tracing or integrations to their code, instrument an LLM application, or needs reference for Opik SDK usage (Python, TypeScript, REST API). Use for tasks like "add tracing", "instrument my code", "use trackopenai", "add OpikTracer", "what span types are…
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
hyper-plan
Use when about to start a non-trivial implementation that needs decomposition before coding. Also when the user invokes /hyperclaude:hyper-plan. Produces an ordered, bite-sized plan in .hyperclaude/plans/ — the input for /hyperclaude:hyper-plan-review and /hyperclaude:hyper-implement.
codex-review
Get a second opinion from OpenAI Codex on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. Use when user asks to "review with Codex", "Codex code review", or "ask Codex to check my code".