Irrlicht: Skill for Claude Code

.claude/skills/ir:agent-releases/SKILL.md

ir:agent-releases is a skill for Claude Code from ingo-eichhorst/Irrlicht. It costs 108 tokens per session (3,617 once invoked), scanned A, original, MIT.

A monitor for new releases of coding agents such as Claude Code, Codex, Pi, Aider, and Gemini CLI. It compares releases with changes that could affect session monitoring in irrlicht.

In plain words
What is it for?
Checking supported agents for new releases, investigating relevant behavior changes, comparing them with previously tracked versions, and reporting only new monitoring risks or features.
Why use it?
It filters general release news down to updates that may change how monitored agent sessions are recorded or interpreted.

Skill for Claude Code

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

This is ingo-eichhorst/Irrlicht's own configuration. It tells Claude Code how to work on Irrlicht 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 Irrlicht configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ingo-eichhorst/Irrlicht. 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/ingo-eichhorst/Irrlicht/main/.claude/skills/ir:agent-releases/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ingo-eichhorst/Irrlicht

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 ir:agent-releases

README.md
[![agentmods](https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-agent-releases/github.svg)](https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-agent-releases)
Your own site
<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-agent-releases"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-agent-releases/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 ir:agent-releases

Your own site · 80×15
<a href="https://agentmods.dev/skills/ingo-eichhorst/irrlicht/ir-agent-releases"><img src="https://agentmods.dev/badge/skills/ingo-eichhorst/irrlicht/ir-agent-releases.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,617 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 48
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00108 $0.03617
Opus 5 $0.00054 $0.01809
Sonnet 5 $0.00022 $0.00723
Haiku 4.5 $0.00011 $0.00362

Measured 8d ago against content hash 6ea28493eae0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ir:agent-releases scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

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

- Fetch: `https://raw.githubusercontent.com/Aider-AI/aider/main/HISTORY.md` (curl it — a summarizer returned a stale read of this file)
.claude/skills/ir:agent-releases/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Release Monitor for Irrlicht

Check latest releases of supported coding agents, compare against previously tracked releases, and report only new changes that impact irrlicht's session monitoring.

Workflow

1. Load Context

Read these reference files (relative to this skill's directory):

  • references/monitoring-surface.md — what irrlicht monitors and what breaks it
  • references/tracked-releases.md — previously analyzed releases (skip these)

2. Fetch Latest Releases

Sources below were verified on 2026-07-15. Prefer the named URL over a search — several agents have moved repos or have release pages that lag reality, and the guesses this skill used to carry cost real time.

Changelogs are a starting point, not evidence. The 2026-07-15 run's two highest-severity findings (vibe's in-place messages.jsonl rewrite, vibe's readread_file rename) were undocumented upstream, and its two most serious Claude Code findings came from inspecting ~/.claude/projects on this machine, not from any release note. For anything that would be HIGH if true, confirm at source (clone + diff at tags, or raw.githubusercontent.com) or on disk. Conversely, do not report a HIGH from changelog prose alone — the same run produced four plausible-but-false findings that source/disk checks killed.

Where an agent is installed locally, check the local install and its real files — that is the strongest evidence available, and it caught things no changelog mentioned. Note the version you verified against, since it may lag the newest release.

⚠️ grep in this repo is ugrep with -I and will silently return 0 matches on transcript .jsonl files (long lines read as binary). Use python3, rg -a, or git grep when censusing transcripts — a naive grep nearly buried three real findings.

Claude Code
  • Fetch: https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md (full, authoritative)
  • Also: https://docs.anthropic.com/en/docs/claude-code/changelog, GitHub releases API for tag dates
  • Note: version accounting is imperfect — some versions have changelog entries but no release tag, and some have a tag but no entry (e.g. v2.1.177). Do not guess at missing entries.
  • Focus on: transcript format, tool names, permission system, process lifecycle, new agent modes, subagent changes
  • Check ~/.claude/projects directly — the transcript store is recursive (<session>/subagents/, tool-results/, workflows/, session-memory/), and relocated / worktree-state events are not documented anywhere

Read the full file on GitHub · 193 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. 8d ago Changed · +11 tokens per session 6ea28493eae0
  2. 12d ago First seen · 193 lines · 97 tokens per session scan A 3630bb37156a

Subscribe to this mod's changes

ir:agent-releases is a skill published in the GitHub repository ingo-eichhorst/Irrlicht (98 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 3,617 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.