What is olkcli AGENTS.md?

Repository instructions for olkcli, a command-line program for Microsoft services such as email, calendars, contacts, and tasks.

Use them when developing olkcli features involving Microsoft Graph, OAuth sign-in, mail, calendars, contacts, or to-do lists.

They show how the code is organized and how to build, authenticate, test, and follow project conventions when making changes.

olkcli AGENTS.md — Instructions file by rlrghb

Install

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.

agentmods

npx agentmods add instructions/rlrghb/olkcli/agents-md

Clone the repo

git clone --depth 1 https://github.com/rlrghb/olkcli

Made for: Codex, OpenCode.

Per session 2,806 This file is loaded in full into every session.

When invoked 2,806 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02806	$0.02806
Opus 5	$0.01403	$0.01403
Sonnet 5	$0.00561	$0.00561
Haiku 4.5	$0.00281	$0.00281

Measured 2d ago against content hash ff7b8156ca9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

olkcli 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 2d 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.

AGENTS.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure

cmd/olk/: CLI entrypoint — minimal, delegates to internal/cmd.Execute().
internal/cmd/: Command implementations using kong structs. Each command group has its own file(s): mail_*.go, calendar*.go, todo.go, todo_checklist.go, todo_attachments.go, todo_links.go, whoami.go, etc.
internal/msauth/: Microsoft OAuth2 implementation — device code flow, authorization-code + PKCE browser flow (loopback listener), token refresh, credential bridge.
internal/graphapi/: Microsoft Graph API wrapper — mail, calendar, contacts, todo (tasks, checklist items, attachments, linked resources), availability, mailbox settings, mail rules, people. Includes the targetUser helper that routes reads to /me or /users/{id} for delegated mailbox access, and error-shaping helpers (graphErrorMessage, enterpriseError, scopeUpgradeError) in validate.go.
internal/config/: Configuration paths via os.UserConfigDir (~/.config/olk/ on Linux, ~/Library/Application Support/olk/ on macOS, %AppData%\olk\ on Windows).
internal/secrets/: OS keyring integration via 99designs/keyring.
internal/outfmt/: Output formatting — JSON envelope, aligned tables, TSV, timezone conversion via ConvertTime().
SKILL.md: Agent Skills standard file — teaches AI assistants (Claude Code, OpenClaw, etc.) how to use olk commands.
docs/: user-facing guides — enterprise-setup.md walks tenant admins through creating an Entra app registration for --browser.
contrib/: helper scripts — create-entra-app.sh automates the Entra app registration, admin consent, and assignment via the az CLI.
bin/: build outputs (gitignored).

Build, Test, and Development Commands

make build: build bin/olk with version ldflags.
make test: run tests with race detector.
make lint: run golangci-lint.
make install: build and copy to $GOPATH/bin.
make clean: remove bin/.
make version: print current version/commit/date.

Read the full file on GitHub · 92 lines

Changes

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.

2d ago First seen · 92 lines · 2,806 tokens per session scan A ff7b8156ca9b

Subscribe to this mod's changes

olkcli AGENTS.md is an instructions file published in the GitHub repository rlrghb/olkcli (17 stars, last pushed 3d ago), licensed MIT. It adds 2,806 tokens to every session, about $0.0140 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.

Productivity Security Testing calendar contacts email microsoft openclaw outlook

olkcli AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Repository Guidelines

Project Structure

Build, Test, and Development Commands

What this file has done since we first saw it

Other instructions, from other repositories

outlook-mcp CLAUDE.md

outlook-ews-mcp AGENTS.md

outlook-ews-mcp CLAUDE.md

cli AGENTS.md

calendar-mcp copilot-instructions.md

calendar-mcp CLAUDE.md