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 opendatahub-io/ai-helpers --skill github-sync-upstreamgit clone --depth 1 https://github.com/opendatahub-io/ai-helpersWrote 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/opendatahub-io/ai-helpers/github-sync-upstream)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/github-sync-upstream"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/github-sync-upstream/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/opendatahub-io/ai-helpers/github-sync-upstream"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/github-sync-upstream.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 | $0.00100 | $0.01230 |
| Opus 5.5 | $0.00040 | $0.00492 |
| Sonnet 5.5 | $0.00020 | $0.00246 |
| Haiku 4.5 | $0.00010 | $0.00123 |
Grade A, and why
github-sync-upstream 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 7d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Upstream
Merge upstream commits into a sync branch on the user's fork and open a
PR to the target repo. See references/workflow.md for exact script
invocations, exit-code handling, and the summary template.
Commit SHA (optional): $ARGUMENTS
Step 1: Determine Working Context
REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null) || REPO_ROOT=""
If REPO_ROOT is non-empty, run scripts/detect-remotes.sh --repo "${REPO_ROOT}"
and ask via AskUserQuestion whether this is the correct repo.
If yes → Step 2A. If no or not in a repo → Step 2B.
Step 2A: In-Repo Setup
Pre-fill upstream/target from detect-remotes output. Ask via
AskUserQuestion to confirm: upstream repo, target repo, branches
(default main). Run scripts/setup-remotes.sh, parse UPSTREAM_REMOTE and
TARGET_REMOTE. Save ORIGINAL_BRANCH from current HEAD.
Step 2B: Clone From Scratch
Ask for upstream repo, target repo, and branches. If the user has a
local clone, use its path and continue as Step 2A. If not, ask if they
have a GitHub fork — run scripts/clone-fork.sh then scripts/setup-remotes.sh. If
no fork exists, ask them to create one and re-run. Stop.
Save ORIGINAL_BRANCH from current HEAD.
Step 3: Protected Files
Protected files keep the target version, discarding upstream changes.
Ask via AskUserQuestion for glob patterns to protect (or none).
Suggest common examples: /OWNERS, /OWNERS_ALIASES, .tekton/*.yaml,
Dockerfile*konflux.
Anchor ownership patterns to the repo root with a leading /. A bare
OWNERS* matches by basename and so also deletes nested OWNERS files that
upstream owns (e.g. pkg/.../OWNERS), which is rarely intended — only the
root OWNERS / OWNERS_ALIASES are usually target-specific.
Step 4: Pre-flight Check
Verify origin does not point to upstream or target. If it does, tell
the user to set origin to their personal fork and stop.
Step 5: Merge
Run scripts/sync-merge.sh. Handle exit codes 0 (success), 1 (conflicts),
3 (a sync branch for this upstream tip already exists — it may be orphaned or
push-only, so check whether a PR is actually open for it before telling the
user one is), and 4 (nothing to sync — target already up to date; report and
stop, no PR) as described in references/workflow.md.
What ships with it
8 files 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.
- references/conflict-resolution.md 2.7 KB
- references/remote-detection.md 2.9 KB
- references/workflow.md 5.1 KB
- scripts/clone-fork.sh 1.7 KB runs code
- scripts/detect-remotes.sh 1.2 KB runs code
- scripts/open-pr.sh 6.4 KB runs code
- scripts/setup-remotes.sh 2.4 KB runs code
- scripts/sync-merge.sh 8.4 KB runs code
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.
- 7d ago Changed · +32 lines 8e281ec03ea8
- 1mo ago First seen · 80 lines · 100 tokens per session scan A e9ab17c47a49
github-sync-upstream is a skill published in the GitHub repository opendatahub-io/ai-helpers (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 1,230 once invoked, about $0.0004 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
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
ainb-fleet:ainb-spawn
Spawn a coding-agent session correctly with ainb run: always into a git worktree, never bare into a plain checkout. Use whenever you are about to start a Claude/Codex/Gemini/Copilot session in a terminal. Guards the invocations that silently produce a (broken) workspace row, two agents sharing one working tree, a…
Finishing a Development Branch
Clean branch finalization, squashing commits, and updating changelogs before merging.