Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jhlee0409/omni-harness-kit/plugin install harness-kitWrote 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/jhlee0409/omni-harness-kit/assess)<a href="https://agentmods.dev/skills/jhlee0409/omni-harness-kit/assess"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/assess/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/jhlee0409/omni-harness-kit/assess"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/assess.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 | $0.00129 | $0.01027 |
| Opus 5 | $0.00064 | $0.00513 |
| Sonnet 5 | $0.00026 | $0.00205 |
| Haiku 4.5 | $0.00013 | $0.00103 |
Grade A, and why
assess 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 12d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
assess — rank maintenance risk, propose discrete fixes
Give a codebase a stack-parameterized maintainability snapshot so the next change (by a human or an agent) lands where it hurts least. This is deliberately NOT a quality daemon: it is a one-shot, on-demand, read-only audit that outputs a ranked fix list, not a stored score, grade, dashboard, or trend line.
Scope boundary (read this first)
The kit ships no measurement / self-evolving subsystem by design (introspect
SKILL §3, Tier 3). This skill is compatible with that decision because it is a
human-invoked one-shot assessment, not a generated runtime metrics layer: it
persists nothing, runs only when asked, and its output is discrete PRs a person
chooses — never an automatic remediation loop or a number the harness optimizes.
If you find yourself wanting to store the score or run this on every commit,
stop: that is the rejected metrics layer.
Honest limit: there is no validated universal "AI-maintainability" metric. The signals below are structural proxies; hotspots (churn × size) have the strongest maintenance-pain evidence in the literature, static-analysis smells the weakest (they need size/churn controls). Report proxies, not verdicts.
1. Run the engine
bash "${CLAUDE_PLUGIN_ROOT}/skills/assess/assess.sh" <target>
It reuses introspect/detect.sh for the stack, then emits JSON:
signals.hotspots— files ranked by size × 90-day churn (the primary signal).signals.size_outliers— files ≥ 400 lines (hard to change safely).signals.test— is there a runnable verify command + any test files?gap: truemeans an agent can't cheaply prove a change here.signals.lint_debt— the stack linter's finding count, only if it's installed.signals.duplication— candidate clone blocks (8+ identical normalized lines seen in ≥2 places), with locations; conservative, so treat as leads not verdicts.caveats— always surface these to the reader.
The engine is deterministic and cheap (git + wc + a rolling-hash clone scan +
optional installed linter). It does NOT cover dependency cycles or cognitive
complexity yet — say so; don't imply it did.
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.
- 12d ago First seen · 86 lines · 129 tokens per session scan A c3a32b48545d
assess is a skill published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 1,027 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
triage-report
Drain the .review/ report queue. Resolves un-triaged scan/audit reports (producer-agnostic — check-docs-consistency and any other scanner), dispatches the triage-report subagent (Sonnet) one report at a time for per-finding dispositions (promote / patch / dup / needs-investigation / dismiss), then the gateway absorbs…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.
ralphctl-code-review-and-quality
Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when acting as the evaluator assessing a generator's output, and when reviewing any change before signalling…
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.
commit
A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.