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.
curl -O https://raw.githubusercontent.com/ingo-eichhorst/Irrlicht/main/AGENTS.mdgit clone --depth 1 https://github.com/ingo-eichhorst/IrrlichtWrote 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/instructions/ingo-eichhorst/irrlicht/agents-md)<a href="https://agentmods.dev/instructions/ingo-eichhorst/irrlicht/agents-md"><img src="https://agentmods.dev/badge/instructions/ingo-eichhorst/irrlicht/agents-md/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/instructions/ingo-eichhorst/irrlicht/agents-md"><img src="https://agentmods.dev/badge/instructions/ingo-eichhorst/irrlicht/agents-md.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 | $0.04149 | $0.04149 |
| Opus 5.5 | $0.01660 | $0.01660 |
| Sonnet 5.5 | $0.00830 | $0.00830 |
| Haiku 4.5 | $0.00415 | $0.00415 |
Grade A, and why
Irrlicht AGENTS.md 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.
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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Irrlicht — Development Guide
Short Cuts
- Triage and plan an issue with
/ir:triage #<N>. Execute the approved plan with/ir:exec <N>. The execution skill produces a ready PR and never merges. - Run several tickets at once with
/ir:fleet <N> <N>— it groups by declared file scope, verifies each hand-back with a checker rather than a reading, and merges nothing. See ci-gates.md for the wait and gate-scoping rules a concurrent run depends on. - NEVER RUN: the Workflow tool (multi-agent orchestration) if not explicitly requested (too expensive)
Process Rules
Worktrees share the parent repo's .git dir, so git stash is not isolated per worktree — it's a single shared stack. Concurrent agents stashing in different worktrees can pop each other's WIP. Use a local commit as a checkpoint instead (git commit -m wip, amend/reset later).
When encountering suboptimal processes or issues make improvment suggestions in you final answer to the user.
Dismissals carry evidence. Any claim whose function is "you don't need to look here" — already fixed in #X, self-heals, likely benign, non-issue — gets the same bar as the claim it supports: cite what you ran or read, or mark it assumed. This binds wherever a finding is written down (issue bodies, PR descriptions, triage comments, final answers), because a wrong dismissal is the one kind of error that stops anyone from checking it. Marking works: in #1088 every claim explicitly labelled "unverified" was investigated and came back not real, while that issue's one real bug hid in an unmarked aside.
Build Artifacts
Use ./.build for build artifacts.
Building the daemon
- Release builds:
tools/build-release.shreads the base version fromversion.jsonand produces signed universal binaries + the installer. The binary's--versionoutput is the bare version (e.g.0.3.13) so release tags stay clean. - Dev builds:
tools/build-dev.shproduces a native binary atcore/bin/irrlichdwith a version string like0.3.13+1f702e7.dirty— base version plus short SHA plus.dirtyif the worktree has uncommitted changes.+is semver build metadata so dev binaries never compare as "newer" than their base release. - The string is computed by
tools/version.sh(pass--basefor the bare version.json value).promote-recording.shcaptures it into archive and top-levelmanifest.jsonfiles so the viewer's metadata panel shows which dev build produced each recording.
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.
- 1mo ago Changed · +6 tokens per session 8173d0aa2315
- 1mo ago Changed · +4 lines · +75 tokens per session 017f34dfb57b
- 1mo ago Changed 2404c3f28c32
- 1mo ago Changed · +8 lines · +150 tokens per session ec3a43f6b6b6
- 1mo ago Changed · -3 lines · -30 tokens per session 449789ed8fc3
- 1mo ago Changed · +7 lines · +117 tokens per session c22d898848aa
- 1mo ago First seen · 244 lines · 3,831 tokens per session scan A f172d6c7d698
Irrlicht AGENTS.md is an instructions file published in the GitHub repository ingo-eichhorst/Irrlicht (101 stars, last pushed today), licensed MIT. It adds 4,149 tokens to every session, about $0.0166 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.