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/snyk/snyk-ls/agents-mdgit clone --depth 1 https://github.com/snyk/snyk-lsWrote 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/snyk/snyk-ls/agents-md)<a href="https://agentmods.dev/instructions/snyk/snyk-ls/agents-md"><img src="https://agentmods.dev/badge/instructions/snyk/snyk-ls/agents-md.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 5.1 | $0.01338 | $0.01338 |
| Opus 5 | $0.00669 | $0.00669 |
| Sonnet 5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
snyk-ls AGENTS.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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
snyk-ls (snyk/snyk-ls) is the Snyk Language Server, a Go implementation of the Language Server Protocol (LSP) that IDE plugins (vscode-extension, snyk-intellij-plugin, snyk-eclipse-plugin, snyk-visual-studio-plugin) embed via stdio/JSON-RPC to run Snyk scans. It integrates Snyk Open Source (SCA), Snyk Code (SAST), Snyk Infrastructure as Code (IaC), and Snyk Secrets. OSS and IaC use the Snyk CLI as a data provider; Code uses the Snyk Code API. It also exposes an MCP server (mcp_extension/) and a go-application-framework workflow (ls_extension/) that lets the Snyk CLI invoke the language server as an extension.
Build & Development Commands
make tools # install golangci-lint, go-licenses, pact, and git hooks
make build # go build -> build/snyk-ls.<GOOS>.<GOARCH>
make run # go run main.go --reportErrors
make test # go test -timeout=90m -failfast ./... (+ make test-js)
make test-integ # alias for INTEG_TESTS=1 make test
make test-smoke # SMOKE_TESTS=1, all 4 shards
make test-all # INTEG_TESTS=1 SMOKE_TESTS=1 + all smoke shards
make test-coverage # adds -cover -coverprofile=build/coverage.out
make test-live PKG=./application/server/ ARGS="-race" # stream failures as they happen
make lint # golangci-lint run ./...
make lint-fix # go fmt + golangci-lint run --fix
make generate # go generate ./... (regenerates gomock mocks)
make verify-generate # fails if `make generate` produces a diff
Tests use testify with a table-driven style (tests := []struct{...}). INTEG_TESTS=1/SMOKE_TESTS=1 (plus SMOKE_SHARD_1..4) gate integration/smoke stages inside make test.
Architecture
main.gois the entry point: it parses flags, initializes the go-application-framework engine/config, and callsserver.Start(engine, ts).application/handles process wiring:application/server(LSP/JSON-RPC handlers),application/di(dependency injection),application/config,application/codeaction,application/watcher,application/entrypoint.domain/holds core business logic:domain/ide(workspace, hover, codelens, treeview, initialize, all LSP-facing) anddomain/snyk(scanner, persistence, remediation, delta, for scan orchestration).infrastructure/contains product/backend integrations:code,oss,iac,secrets,cli(Snyk CLI executor),authentication,learn,analytics,snyk_api,featureflag,filesystem,sentry.internal/holds shared utilities:types(core interfaces/mocks),product(product enum),uri,progress,notification,logging,mcp,storage,vcs,fflags,testsupport/testutil.ast/does lightweight source parsing (e.g.ast/maven/parser.go) used for range/dependency resolution.ls_extension/is a go-application-framework workflow letting the Snyk CLI invoke the LS as an extension (WORKFLOWID_LS).mcp_extension/is an MCP server extension exposing Snyk scanning to MCP clients.
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 First seen · 55 lines · 1,338 tokens per session scan A ee6d8d83c25f
snyk-ls AGENTS.md is an instructions file published in the GitHub repository snyk/snyk-ls (83 stars, last pushed today), licensed Apache-2.0. It adds 1,338 tokens to every session, about $0.0067 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
RG_IDE copilot-instructions.md
Copilot instructions for DevSwat-ResonantGenesis/RG_IDE, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
RG_IDE ai-customization.instructions.md
Architecture documentation for VS Code AI Customization view. Use when working in src/vs/workbench/contrib/chat/browser/aiCustomization.
RG_IDE tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
RG_IDE interactive.instructions.md
Architecture documentation for VS Code interactive window component. Use when working in src/vs/workbench/contrib/interactive.
RG_IDE notebook.instructions.md
Architecture documentation for VS Code notebook and interactive window components. Use when working in src/vs/workbench/contrib/notebook/.
RG_IDE telemetry.instructions.md
Use when asked to work on telemetry events.