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 Netcracker/qubership-ai-packages --skill triage-dependency-prsgit clone --depth 1 https://github.com/Netcracker/qubership-ai-packagesWrote 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/netcracker/qubership-ai-packages/triage-dependency-prs)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/triage-dependency-prs"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/triage-dependency-prs/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/netcracker/qubership-ai-packages/triage-dependency-prs"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/triage-dependency-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00089 | $0.01282 |
| Opus 5 | $0.00044 | $0.00641 |
| Sonnet 5 | $0.00018 | $0.00256 |
| Haiku 4.5 | $0.00009 | $0.00128 |
Grade A, and why
triage-dependency-prs 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 11d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage dependency-update PRs
Work out why checks are failing on dependency-update PRs and get them back to green. When the user names a PR number, triage that PR; with no number, process every open dependency-update PR that has a failing check.
This covers Renovate (hosted and self-hosted, including fork mode) and Dependabot. The bot determines how you push a fix and how you request a rebase; step 3 covers the differences.
Policy (read first)
- Cause is clear: fix it and push to the PR branch.
- Cause is unclear or ambiguous: ask, don't guess.
- Test is flaky: open an issue linking the CI failure, or fix it in a separate PR when the change is a line or two.
- Reproduce and confirm the fix locally before any push, under the same toolchain and command as CI. Don't push what you haven't verified.
Step 1. Find the failing checks
Identify the dependency-update PRs:
-
Hosted bots filter directly:
gh pr list --state open --app renovateandgh pr list --state open --app dependabot. -
Self-hosted Renovate runs under its own app or account, so the
--appslug differs. Fall back to the branch prefix or the shared label:gh pr list --state open \ --json number,author,headRefName,labels,isCrossRepositoryA dependency-update PR has an author of
renovate[bot]ordependabot[bot](or your self-hosted bot account), arenovate/ordependabot/branch prefix, or adependencieslabel.
For each PR:
-
gh pr checks <PR>shows which checks are red and links to their runs. -
Read the real error in the failing run, not the stacktrace around it:
gh run view <run-id> --log-failedStrip ANSI codes and look for the
What went wrong/FAILEDblock, or the first non-zero exit.
Step 2. Classify each failure
- Infrastructure or runner flake:
502/504,context deadline exceeded, Docker Hub / ghcr.io / Actions-cache timeouts, network blips. Re-run the failed jobs withgh run rerun <run-id> --failed. A one-off network error is not worth an issue; a recurring one is probably an ongoing incident, so note it and come back later. - Real regression from the update: the bump itself breaks the build or the compile (API incompatibility, stricter lint defaults, a major version). Fix it, verify locally, and push to the PR branch.
- Pre-existing tech debt the PR surfaces: the failure also exists on the default branch and shows up only because the PR touches these files (super-linter, for instance, lints the diff alone). It is not the bump's fault. Fix it in a separate PR against the default branch, not the bot branch.
- Flaky test in the code: the test is unstable, the default branch is reliably green, and the update touches neither the test nor its code path. Re-run, then open an issue (or fix it in a separate PR when it is a line or two).
- Not a test: PR-title lint,
renovate/artifacts,renovate/stability-days, a Dependabot compatibility score. Usually out of scope or resolved by the bot. Note it.
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.
- 11d ago First seen · 116 lines · 89 tokens per session scan A e3146dcbf96f
triage-dependency-prs is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 89 tokens to every session and 1,282 once invoked, about $0.0004 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
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
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.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.
mantis-critic
Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.
hotpath_bump
Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…
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.