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 lintgit 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/lint)<a href="https://agentmods.dev/skills/redhat-community-ai-tools/harness-eval/lint"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/harness-eval/lint/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/lint"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/harness-eval/lint.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 | $0.00066 | $0.00568 |
| Opus 5 | $0.00033 | $0.00284 |
| Sonnet 5 | $0.00013 | $0.00114 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade C, and why
lint 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 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.
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/broken-references, security/mcp-least-privilege, security/ast-behavioral, content/allowed-tools-auto-approve --> How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lint Setup
Run 108 deterministic rules + system-level analysis on the user's agent setup. No LLM involved. Fast, reproducible, CI-suitable.
Hard Rules
- This skill does NOT read files qualitatively. It does NOT apply rubrics. It does NOT run cross-type checks. For that, use
/review. - Present the data, don't judge. Report findings as-is. Don't add qualitative commentary.
- If everything passes, say so clearly. Don't manufacture problems.
Step 1: Ask Output Preference
Before doing anything else, ask the user:
Where should i present the results?
- Terminal - print the report here in the conversation
- File - write a markdown report to a file (you'll choose the path)
Wait for their answer before proceeding.
Step 2: Run Static Analysis
Determine the setup path. If the user doesn't specify one, use the current working directory.
uvx --from harness-eval harness-eval harness-lint <setup-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 Report
Read report-format.md and format the results following that structure.
Include all sections: inventory, token budget, context utilization, trigger analysis, dependencies, findings, and inspection summary.
At the very end of the report, include the exact timing:
Evaluated with: harness-eval v{version} (claude-code-plugin)
Duration: [X minutes Y seconds]
Get {version} by running: uvx --from harness-eval harness-eval --version
Record the timestamp of your first tool call in Step 2 and compute the exact difference when you finish.
If the user chose terminal: print the report in the conversation.
If the user chose file: write the report as markdown to the path they specified (or suggest lint-report.md in the current directory). Tell them the file path when done.
What ships with it
1 file 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.
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 Changed abb2540d5333
- 9d ago First seen · 61 lines · 66 tokens per session scan C b12d669bbdac
lint 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 66 tokens to every session and 568 once invoked, about $0.0003 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
debug-with-langwatch
Root-cause production errors and misbehaving agent runs with LangWatch. Finds errored traces, inspects spans, checks monitor and evaluator scores, then narrows to a root cause. Use when something is failing or misbehaving in production (errors, bad answers, latency spikes).
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.
eval-triage
Investigate failing experiments and evaluations with LangWatch. Triage a failing experiment run to the exact rows and evaluator scores that regressed, then to a root cause. Use when an experiment fails, scores drop, or evaluations regress.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
debug-live
Guides root-cause investigations with debugging capabilities by setting breakpoints, starting a debug session, stepping through execution, inspecting variables, and tracing symptoms back to their origin. Prefer it for runtime bugs, failing tests, exceptions, crashes, hangs, wrong/null values, and unexpected output…
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.