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/obsidian-owl/specwright/aikido_rulesgit clone --depth 1 https://github.com/Obsidian-Owl/specwrightWhat 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 | $0.00206 | $0.00206 |
| Opus 5 | $0.00103 | $0.00103 |
| Sonnet 5 | $0.00041 | $0.00041 |
| Haiku 4.5 | $0.00021 | $0.00021 |
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.
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.
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.
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.
- 3d ago First seen · 14 lines · 206 tokens per session scan A 9b6d2ece3101
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.
Other instructions, from other repositories
spec-driven-ai-development copilot-instructions.md
Instructions for LiveTrack-X/spec-driven-ai-development, covering sdad protocol, fast start, controls and route, authority and evidence and safety and execution.
aider-desk AGENTS.md
AGENTS.md instructions for hotovo/aider-desk, covering agents.md, common commands, development, type checking and linting and formatting.
neurolink CLAUDE.md
Instructions for juspay/neurolink, covering claude.md, project overview, critical rules, architecture and pattern: factory + registry.
spec-superflow copilot-instructions.md
Instructions for MageByte-Zero/spec-superflow, covering phase guard, ✅ 允许操作, ⛔ 禁止操作 and 🔔 决策点.
gangsta AGENTS.md
Instructions for kucherenko/gangsta, covering contributing to gangsta, what this is, what will not be accepted, skill changes and the laws apply to contributors too.
hashloom CLAUDE.md
Claude Code instructions for davet47/hashloom, covering working rules for hashloom, git is the user's, scope discipline, hashloom develops on hashloom and definition of done: >5x token reduction.