agentmods.dev

trigger-release-build

trigger-release-build is a skill for Claude Code, Codex from HLND2T/CS2_VibeSignatures. It costs 38 tokens per session (865 once invoked), scanned A, original, MIT.

A controlled procedure for starting a new game release build or rebuilding an existing release from the current main branch commit. A commit is a saved set of code changes, and a SHA identifies one precisely.

In plain words
What is it for?
Use it when explicitly asked to publish, rebuild, or republish a game version, while checking the repository, version, release, tag, and source commit.
Why use it?
It prevents publishing from the wrong code, creating inconsistent tags or releases, or starting duplicate work.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

not rated 67repo changed 1mo ago A scan SkillSpector: pass 38 tokens original MIT

Good fit Use it when explicitly asked to publish, rebuild, or republish a game version, while checking the repository, version, release, tag, and source commit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hlnd2t/cs2_vibesignatures/trigger-release-build
View source ↗ HLND2T/CS2_VibeSignatures
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 HLND2T/CS2_VibeSignatures --skill trigger-release-build
Clone the repo
git clone --depth 1 https://github.com/HLND2T/CS2_VibeSignatures

Made for: Claude Code, Codex.

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 trigger-release-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/trigger-release-build/github.svg)](https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/trigger-release-build)
Your own site
<a href="https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/trigger-release-build"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/trigger-release-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 trigger-release-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/trigger-release-build"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/trigger-release-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00038 $0.00865
Opus 5.5 $0.00015 $0.00346
Sonnet 5.5 $0.00008 $0.00173
Haiku 4.5 $0.00004 $0.00086

Measured 1mo ago against content hash f17766739712, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trigger-release-build 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/trigger_release_build.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.

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.

.claude/skills/trigger-release-build/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trigger Release Build

Use the bundled script as the only remote-operation entry point. Do not construct an ad-hoc gh workflow run command, accept a user-supplied SHA, move a tag, edit a Release, cancel work, or bypass CI source-artifact preflight.

The local script checks repository/auth access, version selection, duplicate work, and the current origin/main SHA. It does not create a temporary worktree or run full source-artifact preflight locally. All build paths retain their CI source-artifact gates before building or publishing; artifact validation failures are reported in the Actions run.

Procedure

  1. Confirm both release choices with the user before any remote work. Ask two separate questions and do not dispatch until both are answered explicitly — never choose on the user's behalf, never preselect an option, and never infer an answer from a previous run.
    • Build path: offer all three choices:
      • release: fresh -force_all rebuild, with automatic prior-version artifact/signature reuse when available.
      • full-rebuild: fresh -force_all -oldgamever none rebuild of every configured artifact into an empty external output root. No oldgamever artifacts are used as references or old-signatures sources. The execution report must prove no prior GAMEVER and an isolated old-artifact root. Source-controlled preprocessor references remain available; tracked artifacts for the target GAMEVER remain the verification and publication truth.
      • rebuild-free: manual emergency path that binds tracked bin_artifacts/<GAMEVER> without proving rebuildability.
    • Publication: verify-only (verify candidates without publishing), publish (publish without replacing existing content), or republish (replace an existing mutable Release in place, retaining its ID and tag name). In Claude Code, ask with the AskUserQuestion tool, offering the available choices on each question.
  2. Extract the requested game version, or use latest only when the user explicitly asks for the latest version.
  3. Map the confirmed answers onto the script flags: --mode <verify-only-or-publish-or-republish>, plus --workflow full-rebuild or --workflow rebuild-free when the user chose that path. Omit --workflow for release. full-rebuild dispatches the standard build workflow with source_artifact_mode=full-rebuild.
  4. Run from any directory with the confirmed mode stated explicitly:

Read the full file on GitHub · 53 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. 1mo ago Changed · +5 lines f17766739712
  2. 1mo ago Changed · +4 lines 9db0e23f5488
  3. 1mo ago Changed · +11 lines f6d5a24f7b9f
  4. 1mo ago Changed · +3 lines 833b48333e28
  5. 2mo ago Changed · +1 lines · -3 tokens per session ab340192bc6e
  6. 2mo ago First seen · 29 lines · 41 tokens per session scan A a14cd009b8f6

Subscribe to this mod's changes

trigger-release-build is a skill published in the GitHub repository HLND2T/CS2_VibeSignatures (67 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 865 once invoked, about $0.0002 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.

Game developmentGit and workflowReleases
Related

trigger-release-build compared with skills from other repositories

trigger-release-build next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
trigger-release-buildHLND2T/CS2_VibeSignaturesSkill67todayMITA38Claude Code, Codex
build-game-changelogMengTo/SkillsSkill7.3kyesterdayMITA100Codex
writing-modpack-changeloghashgraph-online/awesome-codex-pluginsSkill1.5kyesterdayApache-2.0A69Claude Code, Codex
flame-harness-buildtjdrhs90/flutter-flame-harnessSkill6110d agoMITA38Claude Code
releaseyurineko73/Godot-MCP-NativeSkill8713mo agoMITA29Claude Code, Codex
roblox-publish-checklistTabooHarmony/roblox-brainSkill16222d agoMITA27Claude Code
changelogfrabcd/codex-ai-game-studioSkill2110d agoMITA29Codex