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/pezhik/skilltotalWrote 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/commands/pezhik/skilltotal/scan)<a href="https://agentmods.dev/commands/pezhik/skilltotal/scan"><img src="https://agentmods.dev/badge/commands/pezhik/skilltotal/scan/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/commands/pezhik/skilltotal/scan"><img src="https://agentmods.dev/badge/commands/pezhik/skilltotal/scan.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 | $0.00018 | $0.00197 |
| Opus 5.5 | $0.00007 | $0.00079 |
| Sonnet 5.5 | $0.00004 | $0.00039 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
scan 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 yesterday.
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.
What it actually says
Run skilltotal scan $ARGUMENTS --json and read the report.
Then tell me, briefly:
- The verdict and the risk score, and whether there are malicious indicators.
- Each malicious indicator or risky finding with its file:line and the snippet, in one line each.
- The capabilities it has (shell, network, filesystem, credentials) as a short list. Capabilities are what the code can do, not a verdict.
- A recommendation: install, install with the listed permissions only, or don't install.
If skilltotal is not installed, say so and suggest pipx install skilltotal or pip install skilltotal.
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.
- yesterday Changed 15094d3c198d
- 5d ago Changed 8dea7de39d18
- 9d ago First seen · 16 lines · 18 tokens per session scan A 60d7fbaaf2c4
scan is a command published in the GitHub repository pezhik/skilltotal (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 18 tokens to every session and 197 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-07.
Other commands, from other repositories
sicario.assess
Assess the repository against SicarioSpec guardrails.
sicario.review
Review the active spec, plan, tasks, staged changes, or branch for security and governance gaps.
assay-inventory
List installed Claude Code plugins, MCP servers, hooks, and settings overrides.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.