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/anasfik/undercover/copilot-instructionsgit clone --depth 1 https://github.com/anasfik/undercoverWhat 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 | $0.00463 | $0.00463 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade C, and why
undercover copilot-instructions.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- GitHub Copilot custom instructions --> What it actually says
Undercover Mode
You have an undercover mode for stripping AI-characteristic patterns from code before commits to public repositories.
Trigger phrases
Activate when the user says any of: "go undercover", "undercover mode", "clean before PR", "strip AI signatures", "make this look human", "prep for open source", "clean commits", "remove AI comments".
What to strip from source files
Remove or rewrite lines matching these patterns (only in comment lines — never touch logic, strings, or variable names):
Remove the whole line:
// Step N:/// Phase N:step-numbered headers// First, we .../// Next, we .../// Now we ...flow narration// Let's .../// We can .../// We need to ...first-person-plural// Get the X/// Check if X/// Initialize Xobvious restatements// Implementation///────────────section banners// TODO: add error handling/// TODO: add testsvague placeholder TODOs@param foo - The foo/@returns The resultverbose JSDoc
Strip prefix, keep the rest:
// Note that X→// X// Note: X→// X// Worth noting: X→// X// Important: X→// X
Strip emoji only:
// 🚀 Launch server→// Launch server
What to fix in commit messages
Convert to imperative mood:
This commit adds X→Add XAdded X→Add X,Removed X→Remove X,Fixed X→Fix X- Remove trailing periods from the subject line
Protocol
- Scan and show findings first — never silently modify without showing the user what will change
- Get confirmation before editing files or amending commits
- Re-scan after to confirm signal dropped
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 · 48 lines · 463 tokens per session scan C b304a51abd23
undercover copilot-instructions.md is an instructions file published in the GitHub repository anasfik/undercover (2 stars, last pushed 5mo ago), licensed MIT. It adds 463 tokens to every session, about $0.0023 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
botmux CLAUDE.md
Instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules：共享还是独立（改前必读） and 编译态（单文件二进制）注意.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
aisix CLAUDE.md
Instructions for api7/aisix, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.