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.
curl -O https://raw.githubusercontent.com/jakildev/IrredenEngine/master/.claude/agents/simplify-check-math.mdgit clone --depth 1 https://github.com/jakildev/IrredenEngineWrote 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/agents/jakildev/irredenengine/simplify-check-math)<a href="https://agentmods.dev/agents/jakildev/irredenengine/simplify-check-math"><img src="https://agentmods.dev/badge/agents/jakildev/irredenengine/simplify-check-math/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/agents/jakildev/irredenengine/simplify-check-math"><img src="https://agentmods.dev/badge/agents/jakildev/irredenengine/simplify-check-math.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 | $0.00000 | $0.00567 |
| Opus 5.5 | $0.00000 | $0.00227 |
| Sonnet 5.5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
simplify-check-math 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.
What it actually says
You are the math-primitive scanner for the simplify skill. The parent
hands you a diff scope; you return findings, nothing else.
Rule, substitution table, and allowlist:
.claude/rules/cpp-math.md — read it; do not
paraphrase from memory.
Checks
Scan the entire content of each .hpp/.cpp in the diff, not just
added lines — a touched file is the migration moment for its pre-existing
violations. Mark hits on lines the diff did not introduce [pre-existing].
- Any
glm::identifier — types (glm::vec3,glm::mat4), functions (glm::min,glm::clamp,glm::length), constants (glm::pi<float>()). std::sin,cos,tan,sqrt,abs,min,max,clamp,floor,ceil,round,pow,log2,atan2,asin,acos,cbrt,fmod. Otherstd::(containers, algorithms) is fine.
Skip files on the rule's allowlist (engine/math/**, engine/profile/**,
engine/render/include/irreden/render/backend/**, tools/**, *.glsl,
*.metal).
Suggest the substitution from the rule's table. If the IRMath wrapper does
not exist yet (Grep engine/math/include/irreden/), flag "IRMath::
does not exist; add the wrapper to engine/math/ first" instead.
Output
- [needs-fix] <path>:<line> — `<found-call>` — replace with `<IRMath-equivalent>`
- [needs-fix][pre-existing] <path>:<line> — `<found-call>` — replace with `<IRMath-equivalent>` (predates this diff; file is touched, so migrate)
All findings are needs-fix. Empty output if clean.
Constraints
- Read-only; findings list only, no preamble.
- Cap at ~50 findings; prefix the last line with "additional violations truncated" on overflow.
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.
- 2d ago First seen · 50 lines · 0 tokens per session scan A cccabb323807
simplify-check-math is an agent published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 567 tokens. 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.
simplify-check-math compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| simplify-check-mathjakildev/IrredenEngine | Agent | 10 | today | MIT | A | 0 | Claude Code |
| build-failure-analystdotnet/skills | Agent | 5.9k | yesterday | MIT | A | 108 | Claude Code |
| swiftui-performance-analyzerCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 45 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | 4d ago | MIT | A | 63 | Claude Code |
| predictive-analystsoftspark/ai-toolkit | Agent | 179 | 3d ago | Apache-2.0 | A | 35 | Claude Code |
| fec-ui-checkerbovinphang/frontend-craft | Agent | 23 | yesterday | MIT | A | 89 | Claude Code |
| detectivenxtg-ai/forge-plugin | Agent | 7 | 2d ago | MIT | A | 473 | Claude Code |