Agent Orchestrator is a local desktop workspace for running and supervising multiple coding agents, giving each task its own session, workspace, branch, and feedback loop. It is for developers coordinating agent fleets across repositories, pull requests, CI runs, reviews, and merges. The catalogue entries are commands, skills, and instructions for working with this orchestrator.
Borrowing it
Nothing to install: this file belongs to Untrivial-ai/agent-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Untrivial-ai/agent-orchestrator/main/.agents/skills/bug-triage/SKILL.mdgit clone --depth 1 https://github.com/Untrivial-ai/agent-orchestratorWrote 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/untrivial-ai/agent-orchestrator/bug-triage)<a href="https://agentmods.dev/skills/untrivial-ai/agent-orchestrator/bug-triage"><img src="https://agentmods.dev/badge/skills/untrivial-ai/agent-orchestrator/bug-triage/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/untrivial-ai/agent-orchestrator/bug-triage"><img src="https://agentmods.dev/badge/skills/untrivial-ai/agent-orchestrator/bug-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 63 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Rogue Agent · line 368 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00026 | $0.01397 |
| Opus 5.5 | $0.00010 | $0.00559 |
| Sonnet 5.5 | $0.00005 | $0.00279 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
bug-triage 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug triage
Help the reporter describe what they observed and add useful evidence. A short human observation is enough to report a bug; reproduction, logs, and a diagnosis are optional. Use this skill for reports from chat, an existing issue, or a local user.
Clarify the observation
Read the available report, screenshots, and follow-ups first. Preserve the original reporter's words and attribution, including when someone else relays their report. Don't infer a GitHub username from a chat display name.
Ask only questions that would materially clarify the symptom, a few at a time. Don't repeat questions already answered or turn these suggestions into required fields:
- What did you do, and what happened instead of what you expected?
- Where did it happen, and does it happen every time or only sometimes?
- For a visual problem, can you share a screenshot or short recording showing it?
- If relevant, which AO version and OS were you using, and did it start after a change?
If a screenshot is unavailable, accept a description. If the reporter cannot remember steps or reproduce the problem, preserve that uncertainty and proceed with what is known. Never invent steps or make the reporter diagnose the bug before accepting it.
Keep the report and investigation separate
Draft a specific symptom-based title and a short body, normally one paragraph or a few bullets. Include only details supplied directly by the human: their observation, expected behavior, steps, frequency, environment, and impact when they provided them. Light editing for clarity is fine; preserve meaning and uncertainty. Omit empty sections and unnecessary background. Do not add agent-inferred impact, root cause, confidence scores, or proposed fixes to the report.
Example human report:
After I switched projects, the terminal stayed blank. I expected to see the session prompt. It happened twice today on macOS; I don't know how to reproduce it reliably.
Keep agent-discovered information separate from the human report and label it Agent-collected evidence, even when it confirms the report. Include only relevant excerpts and:
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.
- 1mo ago Changed · -3 lines 6ef0c8ae0355
- 1mo ago Changed · -290 lines · -7 tokens per session 6b95d553783e
- 1mo ago First seen · 422 lines · 33 tokens per session scan A 2c6df9861f08
bug-triage is a skill published in the GitHub repository Untrivial-ai/agent-orchestrator (13,596 stars, last pushed 2d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,397 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
worker-debugger
Cortex delegated specialist only: Debugging specialist for reproducing failures, proving root cause, implementing focused fixes, and verifying regressions.
worker-performance-engineer
Cortex delegated specialist only: Performance analyst for bottlenecks, query plans, resource usage, and safe optimization trade-offs.
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
comet-github-issue-fix
A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.