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/discover-workflowsnpx skills add verkyyi/github-agent-runner --skill discover-workflowsgit 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 | $0.00046 | $0.00542 |
| Opus 5 | $0.00023 | $0.00271 |
| Sonnet 5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
discover-workflows 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
discover-workflows
Recommend 1-3 workflows from the upstream githubnext/agentics catalog that fit the user's current repo. No local catalog — every call fetches the latest state from upstream.
Flow
- Detect repo shape: language, framework, test presence, CI presence, size (files, LOC), activity (recent commits). Use
gitand filesystem inspection only — no external calls yet. - Fetch the upstream workflow list:
- Prefer
gh aw list(or equivalent listing verb) if it enumerates upstream workflows. - Otherwise,
gh api repos/githubnext/agentics/contents/workflowsto list available.mdworkflow files, and fetchgithubnext/agentics's README orworkflows/README.mdfor one-line descriptions.
- Prefer
- Short-list ~5 candidates by matching names + descriptions to the detected repo shape. Do NOT read every workflow's body at this stage — that's too many tokens.
- For each short-listed candidate, fetch the workflow's frontmatter only (
gh api repos/githubnext/agentics/contents/workflows/<name>.md→ base64-decode → parse YAML frontmatter). Confirm triggers, required secrets, and fit signals. - Pick 1-3 whose frontmatter genuinely matches the repo shape. The recommendation IS the product — don't fall back to "here's the full list."
- For each recommendation, show: name, one-line purpose, why it fits THIS repo (one sentence, specific), estimated setup friction.
- Ask which (if any) the user wants to install. Hand off to
/install-workflow <name>.
Hard rules
- Never recommend a workflow whose required secrets the repo clearly can't produce (e.g. don't recommend a Slack-notification workflow in a repo with no Slack references anywhere).
- Never recommend more than 3 at once. Two is usually right.
- Never draft a custom workflow. If the user asks for one, point them at
zircote/github-agentic-workflowsand stop. - Never fall back to a stale or inline list if the upstream fetch fails. Surface the error plainly and stop — a broken network beats a stale recommendation.
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 · 34 lines · 46 tokens per session scan A 703f4894edd0
discover-workflows is a skill published in the GitHub repository verkyyi/github-agent-runner (10 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 542 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 2026-08-31.
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.