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.
npx agentmods add instructions/kevinrabun/judges/secure-codinggit clone --depth 1 https://github.com/KevinRabun/judgesWhat 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 | $0.01198 | $0.01198 |
| Opus 5 | $0.00599 | $0.00599 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
judges secure-coding.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure Coding — Preventing CodeQL / Code Scanning Findings
Follow these rules when writing or modifying TypeScript code in this repository. They address the categories of findings that GitHub Code Scanning (CodeQL) flags.
1. Regex Safety (js/polynomial-redos)
Avoid regular expressions that can exhibit catastrophic backtracking.
- Never use nested quantifiers like
(.+)*,(a+)+,(\s*)*, or(\S.*)$with greedy/backtracking groups. - Prefer string methods (
indexOf,startsWith,endsWith,split,substring) over regex when the pattern is a fixed string or simple delimiter. - When regex is necessary, use possessive-style character classes:
[^ \t\n]*instead of.*, and[^\n]*instead of.+. \sin quantified positions is dangerous because it overlaps with[ \t]— prefer explicit[ \t]when you only need horizontal whitespace.- If a pattern is anchored with
$and can only match once, do not use the/gflag. - For parsing structured comment directives (e.g.,
// judges-ignore RULE-ID), useindexOf+substringinstead of a single complex regex.
Bad:
const pattern = /(?:\/\/|#|\/\*)\s*judges-ignore\s+(.+)$/gi;
Good:
const idx = line.indexOf("judges-ignore");
if (idx >= 0) {
const before = line.substring(0, idx).trimEnd();
if (before.endsWith("//") || before.endsWith("#") || before.endsWith("/*")) {
const rest = line.substring(idx + "judges-ignore".length).trimStart();
// ... parse rest with string methods ...
}
}
2. No Sensitive Data in Logs (js/clear-text-logging)
Never log values sourced from process.env — CodeQL treats all environment variables as sensitive.
- Use
os.userInfo().usernameinstead ofprocess.env.USERorprocess.env.USERNAMEwhen you need the current user's name. - If you must read an env var, assign it to a local variable and do not pass that variable to
console.log,console.error, or any logging function.
Bad:
const user = process.env.USER || "unknown";
console.log(`Action performed by ${user}`);
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 · 136 lines · 1,198 tokens per session scan A 903c52d9a997
judges secure-coding.instructions.md is an instructions file published in the GitHub repository KevinRabun/judges (7 stars, last pushed 2mo ago), licensed MIT. It adds 1,198 tokens to every session, about $0.0060 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
drift copilot-instructions.md
Instructions for mick-gsk/drift, covering drift — verbindliche arbeitsgrundlage für alle agenten, primärmodus bei prompt-engineering, zuerst das richtige primitive wählen, nicht verhandelbare schärferegeln and mindestvertrag für jeden guten prompt.
drift drift-push-gates.instructions.md
Nutze diese Instruction, wenn ein Commit, ein Push oder eine Release-Vorbereitung im Drift-Repo ansteht. Sie ist die autoritative Gate-Quelle fuer Pre-Push-Anforderungen, Bypaesse und lokale CI-Pflichten.
drift drift-quality-workflow.instructions.md
Nutze diese Instruction bei nicht-trivialen Aenderungen, Reviews oder Fix-Loops im Drift-Repo. Fokus: adversarialer Gegenreview, iterativer Fix-Loop, expliziter Freigabestatus und Human-in-the-Loop vor Merge.
vibe-check AGENTS.md
Instructions for benavlabs/vibe-check, covering security rules, secrets, database, authentication and authorization and input and output.
drift drift-agent-quickref.instructions.md
Kompakte Task-zu-Gate Kurzanleitung fuer Drift-Agenten. Verwenden fuer schnellen Einstieg bei feat, fix, signal, chore, prompt und review Aufgaben.
drift drift-rag-grounding.instructions.md
Nutze diese Instruction, wenn ein Coding-Agent Behauptungen ueber drifts eigene Policy, Signale, ADR-Entscheidungen, Audit-Ergebnisse oder Benchmark-Evidence aufstellt. Sie verpflichtet zur Zitation verifizierter Fact-IDs via driftretrieve und driftcite (ADR-091).