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 skills/verkyyi/github-agent-runner/install-agent-teamnpx skills add verkyyi/github-agent-runner --skill install-agent-teamgit clone --depth 1 https://github.com/verkyyi/github-agent-runnerWhat 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 | $0.00055 | $0.01841 |
| Opus 5 | $0.00028 | $0.00920 |
| Sonnet 5 | $0.00011 | $0.00368 |
| Haiku 4.5 | $0.00006 | $0.00184 |
Grade A, and why
install-agent-team 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
install-agent-team
Install all four agent-team workflows into the current repo in one pass: fetch, wire auth once, apply the OAuth tweak to every lockfile, create the labels, validate, commit.
The result: the user dispatches a task by adding a single agent-team label to any issue. The four agents coordinate across the thread via structured comments and a small internal state machine.
When to use this
- User says "install agent-team", "set up the agent pipeline", "install the spec/plan/impl/review workflows", or similar.
- User types
/install-agent-team. - User has just heard about the pattern via
/discover-workflowsand asked to install it as a unit.
When NOT to use this
- User wants a single workflow (e.g.
daily-repo-status,repo-assist) — hand off to/install-workflowinstead. - User's repo has no tests AND they want PRs that check passing tests — warn them: the reviewer expects a runnable test command. Offer to install anyway with the caveat that the reviewer will note "no test infrastructure" on every PR.
Flow
1. Explain what's about to happen
One paragraph: four workflows will be added, one auth secret will be set, seven labels will be created, nothing runs until the user opens an issue and adds agent-team. Ask for explicit confirmation to proceed. The user must opt in — workflows run on push.
2. Preflight
Check in parallel:
ghCLI authenticated (gh auth status)workflowscope present on theghtoken (gh auth status -t 2>&1 | grep -i 'token scopes'). Without it, the user's firstgit pushof.github/workflows/*.lock.ymlwill fail with "refusing to allow an OAuth App to create or update workflow ... withoutworkflowscope". If missing, have the user rungh auth refresh -s workflow -h github.com(browser flow, ~30 sec) before continuing.gh awextension installed (gh extension list | grep gh-aw)- Current dir is a git repo clean enough to commit (
git status --porcelain) - User has write access to
origin(gh repo view --json viewerPermission) - Repo Actions settings allow PR creation. Warn the user this must be ON in Settings → Actions → General → "Allow GitHub Actions to create and approve pull requests". The skill cannot flip this.
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.
- 2d ago First seen · 135 lines · 55 tokens per session scan A 68634ef8fd36
install-agent-team is a skill published in the GitHub repository verkyyi/github-agent-runner (10 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 1,841 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
dependency-triage
Scan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
merge-strategy
Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.