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 eric-tramel/moraine --skill bug-reportgit clone --depth 1 https://github.com/eric-tramel/moraineWrote 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/eric-tramel/moraine/bug-report)<a href="https://agentmods.dev/skills/eric-tramel/moraine/bug-report"><img src="https://agentmods.dev/badge/skills/eric-tramel/moraine/bug-report/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/eric-tramel/moraine/bug-report"><img src="https://agentmods.dev/badge/skills/eric-tramel/moraine/bug-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.01197 |
| Opus 5.5 | $0.00012 | $0.00479 |
| Sonnet 5.5 | $0.00006 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
bug-report 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 1mo 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Report
Use this skill when the user hit a likely Moraine defect and wants help turning it into a useful GitHub issue. A Moraine bug is a reproducible problem in the Moraine CLI, ingest, monitor, MCP server, setup flow, packaging, documentation, or bundled plugins.
Do not use this skill for general support, one-off local setup help, unrelated agent-harness issues, or private debugging that cannot be generalized into a Moraine repository issue. Troubleshoot those locally instead, and file a report only if the evidence points to a fixable Moraine defect.
Destination
The Moraine repository is:
https://github.com/eric-tramel/moraine
New bug reports go through GitHub Issues:
https://github.com/eric-tramel/moraine/issues/new
If a GitHub issue tool, browser, or gh is available, use it only after the
user explicitly confirms the final redacted report. If no posting tool is
available, provide the issue URL and the prepared report body.
Consent Boundary
Never silently post an issue on the user's behalf. Even if the user says "file it", first show the final sanitized title and body, then ask for explicit confirmation before creating the issue. If the user declines, stop after providing the draft.
Do not upload logs, configs, screenshots, session transcripts, or command output without the same explicit confirmation.
Privacy Rules
All bug reports must anonymize PII and host-specific details before they leave the user's machine.
Redact or generalize:
- Usernames, hostnames, emails, organization names, repo names, client names, and internal project names.
- Exact absolute paths such as home directories, workspace roots, socket paths, and temp directories.
- Secrets, tokens, API keys, cookies, auth headers, database URLs, and credentials.
- Private prompts, agent transcripts, file contents, logs, or screenshots unless the user explicitly approves a minimal sanitized excerpt.
- Exact host environment details that fingerprint the machine. Prefer broad labels like "macOS on Apple Silicon", "Linux x86_64", "Homebrew install", or "uv tool install" instead of full hardware, hostname, local account, or full directory layouts.
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.
- 1mo ago First seen · 160 lines · 29 tokens per session scan A 096a7c2778f8
bug-report is a skill published in the GitHub repository eric-tramel/moraine (116 stars, last pushed 12d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,197 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
debug-gateway
Load this before concluding a change did not land, and to read what the kirocrew-debug tools actually answered - which question to ask first, the fields that mean the opposite of how they look, and what a 400 / 403 / 404 / 501 from these tools means.
ai-discover
Read-only discovery step of the auto-improvement loop. One bounded agent turn per cycle reads the focus files (Read/Grep/Glob only, no shell, no subagents) and replies with a JSON array of testable surfaces {file, line, symbol, rule, message, hypothesis}; the spine authors fixes and verifies them. Discovery only — no…
debug
Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out, returning errors, or behaving unexpectedly. Forces structured root-cause analysis before any code change is proposed.