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 redhat-community-ai-tools/harness-eval --skill skill-verifygit clone --depth 1 https://github.com/redhat-community-ai-tools/harness-evalWrote 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/redhat-community-ai-tools/harness-eval/skill-verify)<a href="https://agentmods.dev/skills/redhat-community-ai-tools/harness-eval/skill-verify"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/harness-eval/skill-verify/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/redhat-community-ai-tools/harness-eval/skill-verify"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/harness-eval/skill-verify.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 | $0.00348 |
| Opus 5 | $0.00024 | $0.00174 |
| Sonnet 5 | $0.00010 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade C, and why
skill-verify scanned grade C with 1 finding 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- evaluator-ignore: content/allowed-tools-auto-approve --> What it actually says
Skill Verify
Vet a skill or setup for security and quality issues before installing.
Hard Rules
- Run the CLI command. Do not skip the scan.
- Report the verdict clearly. SAFE, CAUTION, or UNSAFE.
- Show all findings with fix suggestions.
Step 1: Get the Path
Ask the user for the path to the skill or setup directory to verify. If they provide a URL, clone it first:
git clone --depth 1 <url> /tmp/skill-to-verify
Step 2: Run the Scan
uvx --from harness-eval harness-eval skill-verify <path> --format json
If uvx is not available, fall back to pip install harness-eval and use harness-eval directly.
Read the JSON output.
Step 3: Present the Results
Report the verdict prominently: SAFE, CAUTION, or UNSAFE.
List all findings with their severity, rule, message, and fix suggestion.
If UNSAFE, tell the user not to install without addressing the findings. If CAUTION, tell the user to review the warnings before installing. If SAFE, tell the user it's safe to install.
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.
- 9d ago First seen · 48 lines · 48 tokens per session scan C 1c9fc7bf92e8
skill-verify is a skill published in the GitHub repository redhat-community-ai-tools/harness-eval (27 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 348 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.
developer-setup
One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. After successful setup this skill is excluded from selection until the marker file is deleted.
code-review
Paranoid architect review of code changes for bugs, security, missing tests, and undocumented assumptions. Works on local git diffs OR a GitHub pull request (e.g. owner/repo N). For PRs, can post findings as line-level review comments.
commitment-setup
One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once projects/commitments/README.md exists in the workspace (the file this skill writes as its first step).
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
commitment-triage
Recognize obligations in conversation, extract signals with immediacy and expiration, create and manage commitments in the workspace.