Agent Substrate is a runtime system for running many isolated applications or AI agents on shared computing infrastructure. It manages agent sandboxes throughout their lifecycle, places them on available workers, and routes traffic to them while using technologies such as Kubernetes, microVMs, and gVisor. Its catalogue skills and instructions support operating and developing workflows around this agent runtime.
Borrowing it
Nothing to install: this file belongs to agent-substrate/substrate. 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/agent-substrate/substrate/main/.agents/skills/triage-issues/SKILL.mdgit clone --depth 1 https://github.com/agent-substrate/substrateWrote 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/agent-substrate/substrate/triage-issues)<a href="https://agentmods.dev/skills/agent-substrate/substrate/triage-issues"><img src="https://agentmods.dev/badge/skills/agent-substrate/substrate/triage-issues/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/agent-substrate/substrate/triage-issues"><img src="https://agentmods.dev/badge/skills/agent-substrate/substrate/triage-issues.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 | $0.00066 | $0.02855 |
| Opus 5.5 | $0.00026 | $0.01142 |
| Sonnet 5.5 | $0.00013 | $0.00571 |
| Haiku 4.5 | $0.00007 | $0.00285 |
Grade A, and why
triage-issues 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 6d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Issues
Triage means: read each issue, decide the right labels from the taxonomy below, and
apply them with gh issue edit. Do not remove labels a human has already added unless
they are clearly wrong. Do not add priority labels unless the issue body or discussion
makes the priority obvious.
Two hard rules govern every run:
- Propose before applying. Classify everything first and present the full set of proposed changes as a summary for the user to validate. Apply nothing — no labels, no label creation — until the user approves.
- Record an undo. While applying approved changes, build an undo script that reverses exactly what this run did, and hand the user the command to run it.
Label taxonomy
Every issue should have at least one kind/ label and at least one area/ label.
Priority and status labels are optional.
kind/ — what the issue is
| Label | When to apply |
|---|---|
kind/bug |
Something is broken or behaves incorrectly. The current behavior is wrong. |
kind/feature |
A new capability that does not exist today. Includes enhancements to existing features. |
kind/cleanup |
Code quality improvements that do not change behavior: refactors, naming, dead code removal, small inconsistencies. |
kind/docs |
Documentation only — missing, outdated, or incorrect docs. |
kind/design |
Design discussions, investigations, research, and open questions that must be resolved before implementation. Includes "Design discussion:", "Identify what X should be", "Measure/benchmark X", "Explore options". |
If any label in this taxonomy does not exist on the repo yet, include its creation in the proposal and create it during the apply step with:
gh label create "<label>" \
--repo agent-substrate/substrate \
--description "<short description matching the taxonomy table>" \
--color "c5def5"
area/ — which part of the codebase
Apply all areas that are touched. Most issues need one or two; a few need more.
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.
- 6d ago Changed fbda17ba1873
- 7d ago Changed 7ee964e01ed6
- 14d ago Changed 33ae6311969d
- 1mo ago First seen · 276 lines · 66 tokens per session scan A 2929030cb14d
triage-issues is a skill published in the GitHub repository agent-substrate/substrate (5,957 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 2,855 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
pipeline-conductor
Operating procedure for the kirocrew-pipeline-conductor agent. Use when a pipeline conductor session is seeded, inspected or debugged. You MANAGE one issue/PR pipeline on one repo: two columns per item (session working? item solved?), send intent, never re-derive a red yourself.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
orchestrate
Toolbox for driving HumanLayer from the CLI - log in, pick a host, launch tasks in their own worktrees, launch sessions, list tasks and their PRs, and copy, move, or upload task artifacts.
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.
github-monitor
Watch your GitHub repos across four views - a combined urgency monitor (stale PRs, new issues, releases), a new-issue triage queue, a release upgrade digest, or your own opened-PR tracker.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.