specwright aikido_rules.instructions.md

A set of Aikido security rules for AI-generated, added, or modified first-party code. It requires the code to be scanned for security problems and any findings to be fixed and checked again.

In plain words
What is it for?
Use it to enforce full Aikido scans, remediation, and repeat scans until the changed code has no remaining findings.
Why use it?
It adds a required security check to the coding workflow and prevents unresolved scanner findings from being left in new or changed code. If the Aikido server is unavailable, it directs the user to its setup guide.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/obsidian-owl/specwright/aikido_rules
Clone the repo
git clone --depth 1 https://github.com/Obsidian-Owl/specwright

Made for: GitHub Copilot.

Per session 206 This file is loaded in full into every session.
When invoked 206 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00206 $0.00206
Opus 5 $0.00103 $0.00103
Sonnet 5 $0.00041 $0.00041
Haiku 4.5 $0.00021 $0.00021

Measured 3d ago against content hash 9b6d2ece3101, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specwright aikido_rules.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 3d 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.

Origin

This is a copy

100% identical to unraid-management-agent aikido_rules.instructions.md — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/instructions/aikido_rules.instructions.md · 14 lines

What it actually says

Project security best practices

  • Always run aikido_full_scan on generated, added and modified first-party code, unless the prompt explicitly says not to.
  • Always provide the full file content to the scanner.
  • If the scan identifies any security issues in newly generated or modified code, fix the issues using the scan result and remediation provided by Aikido.
  • After applying fixes, run aikido_full_scan again to verify that the issues were successfully resolved, and no new issues were introduced.
  • Repeat the fix-and-rescan cycle until the code passes with zero remaining or newly introduced security issues.
  • If the Aikido MCP server required to run scans is not installed or not started successfully, inform the user with a message directing them to install it using the official Aikido MCP setup guide at:
    https://help.aikido.dev/ide-plugins/aikido-mcp.
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. 3d ago First seen · 14 lines · 206 tokens per session scan A 9b6d2ece3101

Subscribe to this mod's changes

specwright aikido_rules.instructions.md is an instructions file published in the GitHub repository Obsidian-Owl/specwright (9 stars, last pushed 4mo ago), licensed MIT. It adds 206 tokens to every session, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to unraid-management-agent aikido_rules.instructions.md, differing in 3 lines, and is treated as a copy.