Borrowing it
Nothing to install: this file belongs to jlevy/supply-chain-hardening. 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/jlevy/supply-chain-hardening/main/AGENTS.mdgit clone --depth 1 https://github.com/jlevy/supply-chain-hardeningWrote 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/jlevy/supply-chain-hardening/agents-md)<a href="https://agentmods.dev/instructions/jlevy/supply-chain-hardening/agents-md"><img src="https://agentmods.dev/badge/instructions/jlevy/supply-chain-hardening/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/jlevy/supply-chain-hardening/agents-md"><img src="https://agentmods.dev/badge/instructions/jlevy/supply-chain-hardening/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 | $0.01947 | $0.01947 |
| Opus 5 | $0.00974 | $0.00974 |
| Sonnet 5 | $0.00389 | $0.00389 |
| Haiku 4.5 | $0.00195 | $0.00195 |
Grade B, and why
supply-chain-hardening AGENTS.md scanned grade B with 2 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 8d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
10. Do not run `curl | sh` install commands from untrusted sources. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
10. Do not run `curl | sh` install commands from untrusted sources. How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Entry point for AI coding agents (Claude Code, Codex, Cursor, etc.) working in this repo.
Read README.md first for the full project context.
This file is a fast-path index for the most common agent intents.
For a portable, drop-in version of the install rules that you can copy into any
codebase (and reference from that codebase’s own AGENTS.md), see
SUPPLY-CHAIN-SECURITY.md.
Common Intents
| User Intent | Read This | Then Do This |
|---|---|---|
| “Harden my npm setup” | guidelines/hardening-npm.md |
Apply the Setup section verbatim, starting from Step 0; take the Advanced Setup steps only when their stated situation applies. Verify with the listed pnpm config get / npm config get commands. Append an entry to the user’s supply-chain-audit-log.md (copy from supply-chain-audit-log-template.md) recording what was set. |
| “Harden my PyPI / Rust / Go setup” | guidelines/hardening-pypi.md, guidelines/hardening-crates.md, or guidelines/hardening-go.md |
Same shape: apply the setup, verify, log. |
| “Harden my CI / release pipeline” or “we publish packages” | guidelines/hardening-ci-cd.md |
Apply the publish-side controls (read-only PR caches, SHA-pinned actions, runner egress block, OIDC/staged publishing, provenance monitoring). Most 2026 incidents compromised the publish pipeline, not a consumer. |
| “Harden my agent / editor”, or “is it safe to open this repo?” | guidelines/hardening-agent-workspaces.md |
Apply the workspace-trust and hook-loading policy. Before opening any third-party repo, run uv run scripts/audit_workspace.py ./REPO. Log what was set. |
| “I just installed X. Am I compromised?” | compromised-packages.md first, then the ecosystem’s hardening guide → “Compromise Assessment” section |
For npm: uv run scripts/audit_npm.py --packages <pkg@ver>. For other ecosystems: osv-scanner per the relevant hardening guide. Log findings. |
| “Add a new ecosystem” (RubyGems, NuGet, Hex, Composer, Maven) | self-update-instructions.md → “Adding a New Ecosystem” |
Use the npm pair as the structural template. Cite multiple authoritative sources from README.md → “Incident Reporting Feeds” for any incident claim. |
| “Update the watch list with a new incident” | self-update-instructions.md → Updating compromised-packages.md |
Verify with at least two of the “Incident Reporting Feeds” in README.md. Do not add unverified rumours. |
| “Refresh / fact-check the docs” | self-update-instructions.md and the bead-tracker in .tbd/ |
Use the tbd CLI to track validation work; create a bead per key assertion, verify against README.md → “Authoritative Sources”, fix in place, close with citations. |
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.
- 8d ago First seen · 123 lines · 1,947 tokens per session scan B 35c2d33e196d
supply-chain-hardening AGENTS.md is an instructions file published in the GitHub repository jlevy/supply-chain-hardening (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,947 tokens to every session, about $0.0097 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.