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/marjoballabani/hypergrep/copilot-instructionsgit clone --depth 1 https://github.com/marjoballabani/hypergrepWrote 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/instructions/marjoballabani/hypergrep/copilot-instructions)<a href="https://agentmods.dev/instructions/marjoballabani/hypergrep/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/marjoballabani/hypergrep/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00414 | $0.00414 |
| Opus 5 | $0.00207 | $0.00207 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
hypergrep copilot-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 4d 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
This project has hypergrep installed globally. Use it instead of grep/ripgrep when you need structural understanding of code (function bodies, call graphs, impact analysis). For simple text searches, ripgrep is fine.
When to use hypergrep vs ripgrep:
- Quick text search ->
rg "pattern" .(faster for one-off) - Find + understand a function ->
hypergrep -s "function" . - Search with token budget ->
hypergrep --layer 1 --budget 800 --json "pattern" . - Who calls this / what breaks ->
hypergrep --callers/--impact - Does project use X ->
hypergrep --exists "redis" . - Codebase overview ->
hypergrep --model "" .
Session start:
hypergrep --model "" .-- understand the codebase (run once)hypergrep-daemon --background .-- optional, start if making 10+ searches (auto-stops after 30 min)
Commands:
hypergrep --layer 1 --budget 800 --json "pattern" .-- signatures + call graph in 800 tokenshypergrep -s "pattern" .-- full function bodies (to edit)hypergrep --callers "function_name" .-- who calls this?hypergrep --callees "function_name" .-- what does this call?hypergrep --impact "function_name" .-- what breaks? (run before editing)hypergrep --exists "redis" .-- technology check (NO = guaranteed, YES = likely)
Rules:
- Run
hypergrep --model "" .at session start - Use hypergrep when you need to understand code, rg when you just need to find text
- Run
hypergrep --impactbefore changing any function - Use
hypergrep -sinstead of reading whole files for specific functions
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.
- 4d ago First seen · 28 lines · 414 tokens per session scan A 602e1ef27231
hypergrep copilot-instructions.md is an instructions file published in the GitHub repository marjoballabani/hypergrep (19 stars, last pushed 5mo ago), licensed MIT. It adds 414 tokens to every session, about $0.0021 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 2026-08-30.
Other instructions, from other repositories
codeweave-mcp CLAUDE.md
Instructions for semihkayan/codeweave-mcp, covering claude.md, what this project is, build & run, architecture and layers.
codexray CLAUDE.md
Instructions for NeuralRays/codexray, covering codexray — ai agent instructions, workflow and key principle.
codeseek CLAUDE.md
Instructions for CodeBendKit/codeseek, covering claude.md, build & test, enter rust project directory, build and run tests.
jcodemunch-mcp CLAUDE.md
Claude Code instructions for jgravelle/jcodemunch-mcp, covering jcodemunch-mcp — project brief, current state, key files, cli subcommands and architecture notes.
bonsai-ninja AGENTS.md
Instructions for gromhacks/bonsai-ninja, covering bonsai-ninja, map a codebase, optional explicit semantic sidecar prewarm, explicit spelling for default syntax/construct indexing and optional during active editing.
ariadne AGENTS.md
Instructions for CRJFisher/ariadne, covering guidelines, project layout / intention tree, refactoring ethos, documentation style: canonical and self-contained and scope.