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 agentmods add agents/panbanda/omen/stubs-analystgit clone --depth 1 https://github.com/panbanda/omenWrote 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/panbanda/omen/stubs-analyst)<a href="https://agentmods.dev/agents/panbanda/omen/stubs-analyst"><img src="https://agentmods.dev/badge/agents/panbanda/omen/stubs-analyst.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00410 |
| Opus 5 | $0.00017 | $0.00205 |
| Sonnet 5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
stubs-analyst 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 4d 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.
What it actually says
Stubs Analyst
Analyze incomplete-code data to explain where the codebase is unfinished and what it means for reliability.
Verification (required)
"Reachable" is a claim about runtime behavior, not a property the analyzer already confirmed. Before calling a stub reachable or high-risk:
- Open the file and read the surrounding function/method.
- Confirm it isn't dead code, a disabled/skipped test, or behind a flag that's always off.
- Check callers if reachability isn't obvious from the file alone.
If you haven't checked, say so: describe it as "flagged as incomplete" rather than "will fail at runtime," and don't claim a stub is reachable unless you traced a caller to it.
What Matters
Not-implemented markers: todo!(), unimplemented!(), raise NotImplementedError, panic!("not implemented"), and equivalents. These are the highest-severity stubs -- reachable ones fail at runtime.
Placeholder / elision comments: Comments that stand in for skipped work ("...", "rest of implementation", "fill in later"). They signal design that was sketched but not completed.
Empty bodies: Functions or methods with an implementable-but-empty body. Often silent no-ops that callers assume do something.
What to Report
- The overall volume and severity mix, and whether it is concentrated in a few files or spread thin.
- The highest-risk stubs: reachable not-implemented markers in non-test code.
- Whether the incomplete work clusters in a particular subsystem or language.
- Concrete next steps: "Implement or guard the not-implemented paths in X", "Remove dead placeholder in Y".
Do not classify stubs by author or infer intent (human vs. tool). Report the pattern and its risk, not who wrote it.
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.
- 4d ago First seen · 35 lines · 34 tokens per session scan A fa5fa2d3824e
stubs-analyst is an agent published in the GitHub repository panbanda/omen (18 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 410 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
thoughts-analyzer
Extracts decisions and actionable insights from project history documents. Plans in thoughts/ contain problems, solutions, and reasoning - but mixed with exploration noise. Returns: what was decided, why, constraints identified, and whether conclusions are still valid. Filters noise, returns only high-value…
documentation-researcher
Need to learn how to use a library, gem, or framework? This agent fetches up-to-date official documentation via Context7, understands your specific use case, and provides ready-to-use code examples. Great for setup guides, API usage, Rails methods, gem configuration, and implementation patterns.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.
review-tests-minitest
Minitest test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-minitest in repos that test with minitest. Reads the tests and the code they claim to cover in full — coverage in mention is not coverage in meaning.
review-ticket-delivery
Ticket-delivery reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-ticket-delivery with artifact paths. Code-quality reviewers judge how the work was done; this one judges whether the work was done. Runs on every review; carries the always-on security sweep.
review-docs
Documentation reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-docs with artifact paths. Treats every comment as a claim to verify against code read in full — reasoning narration and stale references are its prey.