Borrowing it
Nothing to install: this file belongs to sneldao/ligis. 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/sneldao/ligis/main/AGENTS.mdgit clone --depth 1 https://github.com/sneldao/ligisWrote 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/sneldao/ligis/agents-md)<a href="https://agentmods.dev/instructions/sneldao/ligis/agents-md"><img src="https://agentmods.dev/badge/instructions/sneldao/ligis/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/sneldao/ligis/agents-md"><img src="https://agentmods.dev/badge/instructions/sneldao/ligis/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 | $0.13474 | $0.13474 |
| Opus 5.5 | $0.05390 | $0.05390 |
| Sonnet 5.5 | $0.02695 | $0.02695 |
| Haiku 4.5 | $0.01347 | $0.01347 |
Grade C, and why
ligis AGENTS.md scanned grade C 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 yesterday.
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 rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install -y libssl-dev pkg-config Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
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.
curl --proto "=https" --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Prune with `rm -rf /opt/ligis-croo/releases/<old>` — never the one `current` 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.
with `curl -skL -o ~/.cache/gltest-direct/genvm-universal-v0.2.12.tar.xz How it starts
The opening of the file, as written. The whole thing — 990 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ligis — Agent Notes
Security floor
CI blocks main on any remaining high/critical npm advisory:
node scripts/security-audit.mjs (self-test: --self-test, raw list:
pnpm run audit:deps:all). Fix rules:
- Direct dep → normal version bump.
- Transitive → add a
pnpm.overridesfloor (rootpackage.json), e.g."follow-redirects": ">=1.16.1". Floors are>=security floors, not pins — Dependabot bumps above them are legitimate (see dependabot.yml). - Unfixable transitive (no reachable patch) → dismiss by policy in BOTH
.github/dependabot.yml(ignore) andscripts/security-audit.mjs(DISMISSED) — the lists are mirrored; CI blocks on a dismissal that exists in only one file. Current dismissals: uuid (GHSA-w5hq-g745-h8pq), decode-uri-component (GHSA-vcc3-ghjq-m6fr) — wallet-SDK client-side transitives.
Casper Contract Build
The Casper contracts use Odra 2.8.1 and require a nightly Rust toolchain.
Building WASM
# From packages/contracts-casper/
# AgentId:
RUSTFLAGS="-C target-feature=-bulk-memory,-bulk-memory-opt" \
ODRA_MODULE=AgentId \
RUSTC_BOOTSTRAP=1 \
rustup run nightly-2026-01-01 cargo rustc \
--release --target wasm32-unknown-unknown \
--bin ligis_contracts_casper_build_contract \
-Zbuild-std=core,alloc \
-- -C linker=/usr/local/bin/wasm-ld
cp target/wasm32-unknown-unknown/release/ligis_contracts_casper_build_contract.wasm wasm/AgentId.wasm
# CredentialRegistry:
RUSTFLAGS="-C target-feature=-bulk-memory,-bulk-memory-opt" \
ODRA_MODULE=CredentialRegistry \
RUSTC_BOOTSTRAP=1 \
rustup run nightly-2026-01-01 cargo rustc \
--release --target wasm32-unknown-unknown \
--bin ligis_contracts_casper_build_contract \
-Zbuild-std=core,alloc \
-- -C linker=/usr/local/bin/wasm-ld
cp target/wasm32-unknown-unknown/release/ligis_contracts_casper_build_contract.wasm wasm/CredentialRegistry.wasm
# GatedVault (credential-gated escrow DeFi primitive):
RUSTFLAGS="-C target-feature=-bulk-memory,-bulk-memory-opt" \
ODRA_MODULE=GatedVault \
RUSTC_BOOTSTRAP=1 \
rustup run nightly-2026-01-01 cargo rustc \
--release --target wasm32-unknown-unknown \
--bin ligis_contracts_casper_build_contract \
-Zbuild-std=core,alloc \
-- -C linker=/usr/local/bin/wasm-ld
cp target/wasm32-unknown-unknown/release/ligis_contracts_casper_build_contract.wasm wasm/GatedVault.wasm
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.
- yesterday Changed · +45 lines · +625 tokens per session 4d10dd6dd66e
- 2d ago Changed · +20 lines · +311 tokens per session ef89a2e5745c
- 4d ago Changed · +79 lines · +1,228 tokens per session scan F → C c8f8751908d5
- 9d ago Changed · +33 lines · +607 tokens per session 9800f6fd2246
- 13d ago Changed · +47 lines · +677 tokens per session 65a34c556ffc
- 15d ago Changed · +34 lines · +571 tokens per session eee5bd64ee45
- 26d ago Changed · +22 lines · +354 tokens per session 86152348945c
- 1mo ago Changed · +28 lines · +416 tokens per session 17f3b03a5d60
- 1mo ago Changed · +105 lines · +1,591 tokens per session e88e22ebe7e3
- 1mo ago First seen · 577 lines · 7,094 tokens per session scan F 36f4282c0255
ligis AGENTS.md is an instructions file published in the GitHub repository sneldao/ligis (2 stars, last pushed today), licensed MIT. It adds 13,474 tokens to every session, about $0.0539 per session on Opus 5.5. A static security scan graded it C 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 2026-08-31.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.