Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.github/instructions/hooks.instructions.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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/vanillagreencom/kendex/hooks)<a href="https://agentmods.dev/instructions/vanillagreencom/kendex/hooks"><img src="https://agentmods.dev/badge/instructions/vanillagreencom/kendex/hooks/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/vanillagreencom/kendex/hooks"><img src="https://agentmods.dev/badge/instructions/vanillagreencom/kendex/hooks.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00235 | $0.00235 |
| Opus 5.5 | $0.00094 | $0.00094 |
| Sonnet 5.5 | $0.00047 | $0.00047 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade C, and why
kendex hooks.instructions.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- generated by bot-instructions from kendex.toml, kendex-local.toml, .kendex-generated.json, SKILL.md, schemas/renders.md, AGENTS.md. Edit [bot-instructions] in the effective manifest or the spec copy, then re-render. What it actually says
hooks/command-safety.sh first refuses recognized unfiltered environment dumps independently of project policy, cwd and Git. Direct named grep permission requires proven newline records; known raw NUL reads need the literal NUL-to-newline tr conversion. Flattened or unproved producer output cannot gain permission. Known nested dumps can refuse conservatively. The project-pattern check separately rejects text matching COMMAND_SAFETY_DENY_PATTERN, read raw and with continuations joined, including quoted text. Nonmatching text passes only that pattern check. An absent setting applies the default systemd-run memory-cap pattern; ^$ disables only pattern matching. Missing payload readers or unreadable input warn and allow the call. Empty or invalid patterns and unavailable policy tools, settings or installed support warn and allow only the pattern check.
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.
- 15d ago Changed · +49 tokens per session 22f964ddc1e5
- 16d ago Changed · +15 tokens per session 7f167c49baed
- 21d ago Changed · -6 tokens per session 891f782c69ba
- 22d ago Changed d142f49123e0
- 23d ago Changed · +26 tokens per session d40fbe15b179
- 29d ago Changed c354d2b4eaeb
- 1mo ago Changed 1cd8e28f559e
- 1mo ago Changed f57eb4904c4a
- 1mo ago Changed · +3 lines · +96 tokens per session scan A → C 4d0643b6c2f4
- 1mo ago First seen · 6 lines · 55 tokens per session scan A 0049376d1756
kendex hooks.instructions.md is an instructions file published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 235 tokens to every session, about $0.0009 per session on Opus 5.5. 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.