Borrowing it
Nothing to install: this file belongs to aldegad/safedeps. 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/aldegad/safedeps/main/AGENTS.mdgit clone --depth 1 https://github.com/aldegad/safedepsWrote 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/aldegad/safedeps/agents-md)<a href="https://agentmods.dev/instructions/aldegad/safedeps/agents-md"><img src="https://agentmods.dev/badge/instructions/aldegad/safedeps/agents-md/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/aldegad/safedeps/agents-md"><img src="https://agentmods.dev/badge/instructions/aldegad/safedeps/agents-md.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 | $0.37359 | $0.37359 |
| Opus 5.5 | $0.14944 | $0.14944 |
| Sonnet 5.5 | $0.07472 | $0.07472 |
| Haiku 4.5 | $0.03736 | $0.03736 |
Grade F, and why
safedeps AGENTS.md scanned grade F with 4 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 5d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **npm enforcement authority = the PostToolUse effect gate** (lockfile closure vs ledger + OSV batch). The PreToolUse command guard is a fast advisory/UX layer, *not* the authority. **It reads npm's two records of a pro Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **npm enforcement authority = the PostToolUse effect gate** (lockfile closure vs ledger + OSV batch). The PreToolUse command guard is a fast advisory/UX layer, *not* the authority. **It reads npm's two records of a pro Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **What a rollback, a refused step, a skipped rebuild and the unfinished-rollback report say is a closed set of line forms, and the output is what is checked.** Every such line is printed by a function in `rust/src/post Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **npm enforcement authority = the PostToolUse effect gate** (lockfile closure vs ledger + OSV batch). The PreToolUse command guard is a fast advisory/UX layer, *not* the authority. **It reads npm's two records of a pro The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 5d ago Changed · +9 lines · +773 tokens per session 29e667f87318
- 9d ago Changed · +82 lines · +1,722 tokens per session dee6f390ec36
- 10d ago Changed · +1,332 tokens per session scan D → F b5eb33050d6a
- 13d ago Changed · +146 lines · +14,781 tokens per session scan C → D 6aafa7f282e8
- 16d ago Changed · +69 lines · +2,461 tokens per session 41e219caa57b
- 17d ago Changed · +83 lines · +12,039 tokens per session scan A → C a016f6dd3ff0
- 1mo ago First seen · 169 lines · 4,251 tokens per session scan A ed2ec9a82838
safedeps AGENTS.md is an instructions file published in the GitHub repository aldegad/safedeps (22 stars, last pushed 6d ago), with no licence file. It adds 37,359 tokens to every session, about $0.1494 per session on Opus 5.5. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.