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/exoscale/cli/agents-mdgit clone --depth 1 https://github.com/exoscale/cliWhat 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 | $0.01674 | $0.01674 |
| Opus 5 | $0.00837 | $0.00837 |
| Sonnet 5 | $0.00335 | $0.00335 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
cli 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 today.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Command pattern - always use RegisterCLICommand
All new commands must use the struct-based pattern.
Do not copy the old flat var cmd = &cobra.Command{...} commands - they
exist in cmd/storage/, cmd/dns/, cmd/dbaas/ and are legacy.
Read this file before writing any new command:
cmd/aiservices/deployment/deployment_create.go
For subcommand placement in an existing group, also read ## Folder layout below.
Skeleton:
type myResourceCreateCmd struct {
exocmd.CliCommandSettings `cli-cmd:"-"`
_ bool `cli-cmd:"create"`
Name string `cli-arg:"#" cli-usage:"NAME"` // required positional
Tag string `cli-arg:"?" cli-usage:"TAG"` // optional positional
Zone string `cli-short:"z" cli-usage:"zone"` // becomes --zone / -z flag
}
func (c *myResourceCreateCmd) CmdAliases() []string { return exocmd.GCreateAlias }
func (c *myResourceCreateCmd) CmdShort() string { return "Create a resource" }
func (c *myResourceCreateCmd) CmdLong() string { return "..." }
func (c *myResourceCreateCmd) CmdPreRun(cmd *cobra.Command, args []string) error {
exocmd.CmdSetZoneFlagFromDefault(cmd)
return exocmd.CliCommandDefaultPreRun(c, cmd, args)
}
func (c *myResourceCreateCmd) CmdRun(_ *cobra.Command, _ []string) error {
// c.Name, c.Zone are already populated here
return nil
}
func init() {
cobra.CheckErr(exocmd.RegisterCLICommand(parentCmd, &myResourceCreateCmd{
CliCommandSettings: exocmd.DefaultCLICmdSettings(),
}))
}
Supported struct tags:
| Tag | Purpose |
|---|---|
cli-cmd:"-" |
Exclude field from CLI processing |
cli-cmd:"name" |
Sets the cobra command name (use on a _ bool field) |
cli-arg:"#" |
Required positional argument |
cli-arg:"?" |
Optional positional argument; []string becomes variadic |
cli-flag:"flag-name" |
Override the auto-derived kebab-case flag name |
cli-short:"z" |
Single-character shorthand |
cli-usage:"text" |
Flag usage string; also used as positional arg label in help |
cli-hidden:"" |
Mark flag hidden |
cli-deprecated:"msg" |
Mark flag deprecated |
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.
- today First seen · 186 lines · 1,674 tokens per session scan A 775e4e9cab6e
cli AGENTS.md is an instructions file published in the GitHub repository exoscale/cli (92 stars, last pushed today), licensed Apache-2.0. It adds 1,674 tokens to every session, about $0.0084 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 2026-09-01.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.