agentmods.dev

IrredenEngine: Skill for Claude Code

.claude/skills/platform-catchup/SKILL.md

platform-catchup is a skill for Claude Code from jakildev/IrredenEngine. It costs 152 tokens per session (6,008 once invoked), scanned A, original, MIT.

A workflow for catching up on pending smoke checks for merged changes on the current computer. It builds demo programs from the main code line, runs them with automatic screenshots, and updates their tracking labels when they pass.

In plain words
What is it for?
Use it to build and run a backlog of demos on Linux, macOS, or native Windows, then mark passing changes as verified and investigate failures.
Why use it?
It removes the need to process each eligible pull request manually when a smoke-test worker was unavailable. It also stops early when the working folder has uncommitted changes or required tools are missing.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is jakildev/IrredenEngine's own configuration. It tells Claude Code how to work on IrredenEngine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything IrredenEngine configures →

not rated 10repo today A scan 152 tokens original MIT
View source ↗ jakildev/IrredenEngine
Reuse

Borrowing it

Nothing to install: this file belongs to jakildev/IrredenEngine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jakildev/IrredenEngine/master/.claude/skills/platform-catchup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jakildev/IrredenEngine

Made for: Claude Code.

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 platform-catchup

README.md
[![agentmods](https://agentmods.dev/badge/skills/jakildev/irredenengine/platform-catchup/github.svg)](https://agentmods.dev/skills/jakildev/irredenengine/platform-catchup)
Your own site
<a href="https://agentmods.dev/skills/jakildev/irredenengine/platform-catchup"><img src="https://agentmods.dev/badge/skills/jakildev/irredenengine/platform-catchup/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 platform-catchup

Your own site · 80×15
<a href="https://agentmods.dev/skills/jakildev/irredenengine/platform-catchup"><img src="https://agentmods.dev/badge/skills/jakildev/irredenengine/platform-catchup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,008 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.
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 $0.00152 $0.06008
Opus 5.5 $0.00061 $0.02403
Sonnet 5.5 $0.00030 $0.01202
Haiku 4.5 $0.00015 $0.00601

Measured 2d ago against content hash 6565ff7dee81, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

platform-catchup 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.

.claude/skills/platform-catchup/SKILL.md · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

platform-catchup

Builds the demo cohort on origin/master, runs it, sweeps the smoke labels on green, fixes forward on red. Label semantics: docs/agents/FLEET-CROSS-HOST-SMOKE.md §"Labels at a glance". This skill is the batch path that clears them when no smoke worker is online for the host.

When

  • The human cues /platform-catchup, "catch up on smoke tests", "process the smoke backlog", or "verify builds the recent PRs".
  • A role banner counted ≥ 5 fleet:needs-<host>-smoke PRs and the human chooses to spend the wall-time.

Skip when the working tree is dirty, or the marker (step 2) matches origin/master and zero PRs are in scope.

Preconditions

  1. git status --porcelain is empty; otherwise print platform-catchup: working tree dirty — commit, stash, or discard before invoking and exit.
  2. fleet-build / fleet-run on PATH (fleet-help for diagnostics; if absent, point at scripts/fleet/install.sh). fleet-build auto-configures; never run cmake --preset (CLAUDE-BASELINE.md §"Hard rules for autonomous fleet roles").
  3. A display. If the first run logs GLFW: failed to create window, downgrade to build-only smoke: sweep only build-clean PRs and flag the missing display in the report.
  4. timeout on PATH. macOS: brew install coreutils and put /opt/homebrew/opt/coreutils/libexec/gnubin ahead of /usr/bin (or alias gtimeout as timeout).
  5. Bash tool usage per CLAUDE-BASELINE.md §"Bash tool rules" — single commands, no cd &&, pipes only to parse wrapper output.

Per-repo configuration

Repo Build cohort
jakildev/IrredenEngine every add_executable(...) across creations/demos/*/CMakeLists.txt plus the lighting/ and z_yaw_rotation/ foreach lists (~41 targets). ir-run --targets --plan is incomplete on some hosts — grep the CMakeLists.
jakildev/irreden IRGame

Read the full file on GitHub · 470 lines

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. 2d ago First seen · 470 lines · 152 tokens per session scan A 6565ff7dee81

Subscribe to this mod's changes

platform-catchup is a skill published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It adds 152 tokens to every session and 6,008 once invoked, about $0.0006 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 2026-11-07.

Git and workflowTesting
Related

platform-catchup compared with skills from other repositories

platform-catchup next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
platform-catchupjakildev/IrredenEngineSkill10todayMITA152Claude Code
merge-batchdiegosouzapw/OmniRouteSkill85kyesterdayMITA46Claude Code
prowler-commitprowler-cloud/prowlerSkill15kyesterdayApache-2.0A44Claude Code, Codex
gh-auth-isolationgithub/gh-awSkill5.6kyesterdayMITA20Claude Code, Codex
comet-githubrpamis/cometSkill3.3kyesterdayMITA72Claude Code, Codex
github-skillzeenie-ai/OpenCompanySkill1.1k4d agoMITA51Claude Code
re0-mergeLilMGenius/paperthinSkill1.4kyesterdayMITA70Claude Code