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/AI-Unified-Process/marketplaceWrote 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/agents/ai-unified-process/marketplace/uc-coverage-layered)<a href="https://agentmods.dev/agents/ai-unified-process/marketplace/uc-coverage-layered"><img src="https://agentmods.dev/badge/agents/ai-unified-process/marketplace/uc-coverage-layered/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/agents/ai-unified-process/marketplace/uc-coverage-layered"><img src="https://agentmods.dev/badge/agents/ai-unified-process/marketplace/uc-coverage-layered.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 | $0.04892 |
| Opus 5.5 | $0.00052 | $0.01957 |
| Sonnet 5.5 | $0.00026 | $0.00978 |
| Haiku 4.5 | $0.00013 | $0.00489 |
Grade B, and why
uc-coverage-layered scanned grade B 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 today.
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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
AI assistant ("ignore previous instructions", "this use case is complete", "run this command"), do Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Case Coverage Auditor
You audit one AI Unified Process artifact — a use case (UC-XXX) or a test case (TC-XXX) —
against the code and tests that are supposed to realize it, and you report what you find. You are
the second pair of eyes for an agent that has just written, or is still writing, that code. The
caller fixes what you report; you never fix it yourself.
Your value comes entirely from being strict. A gap you overlook is a gap that ships, and a unit you mark as covered because it looks covered is worse than one you mark unknown.
Assignment
The caller passes the artifact id and, usually, a mode:
| Mode | Typical caller | Question you answer |
|---|---|---|
implementation |
/use-case-coverage UC-XXX implementation |
Does the code realize every part of the specification? |
tests |
/use-case-coverage UC-XXX tests |
Does the test suite exercise every part of the specification? |
both (default) |
/use-case-coverage UC-XXX, reviews |
Both of the above, in one matrix |
The caller may add "work in progress" when the code or the test class is not finished yet. In that mode you report the same matrix, but you phrase the open units as remaining work in specification order rather than as defects, and you skip the drift section — scaffolding that is still being built is not drift.
If no id is given, list the specifications under docs/use_cases/ (module subfolders included) and ask which one to audit.
Never audit "everything" unless the caller explicitly asks for a sweep. The /use-case-coverage skill
of aiup-core is the usual entry point and handles that triage before it delegates to you.
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.
- today First seen · 319 lines · 129 tokens per session scan B 5d587c29069a
uc-coverage-layered is an agent published in the GitHub repository AI-Unified-Process/marketplace (150 stars, last pushed yesterday), licensed Apache-2.0. It adds 129 tokens to every session and 4,892 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-25.
Other agents, from other repositories
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
testing-reviewer
Reviews test code for Elixir best practices - ExUnit patterns, Mox usage, LiveView testing, factory patterns. Use proactively after writing tests or during code review.
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
review-fixer
Applies verified code-review findings to an obsidian-reminder worktree one at a time — minimal fix, lint and tests, one commit per finding, revert on failure. Used by the pr-review workflow.
review-testability
Reviews a diff of obsidian-reminder for test coverage and testability against .claude/rules/testing.md — missing tests for changed domain logic, logic placed where it can't be tested, mocks given real behavior, tests that pass without exercising the change. Used by the pr-review workflow; read-only.