waiting-for-build

waiting-for-build is a skill for Cursor from kubev2v/forklift-console-plugin. It costs 104 tokens per session (3,349 once invoked), scanned B, original, Apache-2.0.

A workflow for checking MTV tickets on a Jira board that are waiting to be included in a software build. It compares their code changes with build commit hashes and displays the results in an interactive view.

In plain words
What is it for?
Use it to inspect tickets waiting on a build, check their inclusion in a build, and move included tickets to Jira's quality-testing status when appropriate.
Why use it?
It removes the manual work of finding each ticket's merge commit and checking whether that change is already in a build.

Skill for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it to inspect tickets waiting on a build, check their inclusion in a build, and move included tickets to Jira's quality-testing status when appropriate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kubev2v/forklift-console-plugin/waiting-for-build
Install

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.

Any agent
npx skills add kubev2v/forklift-console-plugin --skill waiting-for-build
Clone the repo
git clone --depth 1 https://github.com/kubev2v/forklift-console-plugin

Made for: Cursor.

Wrote 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.

agentmods badge for waiting-for-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/kubev2v/forklift-console-plugin/waiting-for-build/github.svg)](https://agentmods.dev/skills/kubev2v/forklift-console-plugin/waiting-for-build)
Your own site
<a href="https://agentmods.dev/skills/kubev2v/forklift-console-plugin/waiting-for-build"><img src="https://agentmods.dev/badge/skills/kubev2v/forklift-console-plugin/waiting-for-build/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.

agentmods 80×15 button for waiting-for-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/kubev2v/forklift-console-plugin/waiting-for-build"><img src="https://agentmods.dev/badge/skills/kubev2v/forklift-console-plugin/waiting-for-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00104 $0.03349
Opus 5 $0.00052 $0.01674
Sonnet 5 $0.00021 $0.00670
Haiku 4.5 $0.00010 $0.00335

Measured 9d ago against content hash d52ee9206faf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

waiting-for-build scanned grade B with 2 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/fetch-build.py, scripts/query.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

JIRA_API_TOKEN=$(python3 -c "import json; d=json.load(open('.mcp.json')); print(d['mcpServers']['jira-mcp']['env']['JIRA_API_TOKEN'])")

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST \
.cursor/skills/waiting-for-build/SKILL.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Waiting-for-Build Skill

What this does

  1. Queries Jira board 11806 (Migrations & Networking Frontend) — active sprint, MTV quickfilter, "Waiting on build" column (statuses: MODIFIED, Dev Complete).
  2. Finds each ticket's merge commit in the local git repo (searches git log --all for the ticket key).
  3. Checks whether each commit is an ancestor of the latest build tip hashes (fetched automatically from the #mtv-builds Slack channel via fetch-build.py).
  4. Transitions all in_build: true tickets to ON_QA in Jira (transition ID 41).
  5. Renders an interactive canvas (waiting-for-build.canvas.tsx) via the canvas skill.

Default behaviour: transition is always performed. If the user explicitly says "just check" or "don't transition", skip step 4.

Step 0 — Get build tip hashes automatically from Slack

Run fetch-build.py to pull the latest build's commits from the #mtv-builds channel (from the repository root):

python3 .cursor/skills/waiting-for-build/scripts/fetch-build.py

Output example:

{
  "build_label": "IIB 2.12.0-44 | 02.06.2026 19:04 UTC",
  "build_version": "2.12.0",
  "console_plugin_commits": ["8e059c6", "cfc05ae"],
  "mtv_console_plugin_container": "8e059c6f48a7715179038e9bd12151c88c5f9bf1"
}

Pass build_version as --build-version and console_plugin_commits as positional arguments to query.py (Step 1). If console_plugin_commits is empty, fall back to the first 7 chars of mtv_console_plugin_container as the build tip.

How it works: Uses slackdump to archive channel C09DS44AQ65 (#mtv-builds), then queries the SQLite database for the latest IIB build thread.

Credentials are stored in .mcp.json → mcpServers.slack.env:

  • SLACK_TOKENxoxc-... (Red Hat workspace, from Slack desktop app localStorage)
  • SLACK_COOKIExoxd-... (d= cookie from Slack desktop app)
  • SLACK_CHANNEL_IDC09DS44AQ65 (#mtv-builds)
  • SLACKDUMP_WORKSPACEredhat

If fetch-build.py returns an error or empty commits, the Slack session token has expired (they rotate every few hours). Follow this recovery procedure:

Read the full file on GitHub · 297 lines

Files

What ships with it

2 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.

Changes

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.

  1. 9d ago First seen · 297 lines · 104 tokens per session scan B d52ee9206faf

Subscribe to this mod's changes

waiting-for-build is a skill published in the GitHub repository kubev2v/forklift-console-plugin (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 104 tokens to every session and 3,349 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (reads mcp configuration, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories