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/muhammaddadu/outlook-cli/agents-mdgit clone --depth 1 https://github.com/muhammaddadu/outlook-cliWrote 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/muhammaddadu/outlook-cli/agents-md)<a href="https://agentmods.dev/instructions/muhammaddadu/outlook-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/muhammaddadu/outlook-cli/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 | $0.02473 | $0.02473 |
| Opus 5 | $0.01236 | $0.01236 |
| Sonnet 5 | $0.00495 | $0.00495 |
| Haiku 4.5 | $0.00247 | $0.00247 |
Grade A, and why
outlook-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 3d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents (Claude Code, Cursor, Aider, Codex, …) working on this repository.
If you only read one other file, read LEARNINGS.md. It
documents the long sequence of dead ends we hit before landing on the current
architecture. Skim it before proposing alternative approaches — most of the
"obvious" ideas have already been tried and won't work in a locked-down
enterprise tenant.
TL;DR — what this project is
A small Node.js CLI that talks to the Outlook REST API by capturing the
Bearer JWT that Outlook Web (OWA) already uses for its own API calls. It
does this by launching Playwright Chromium against the user's persistent
profile, watching the network for the first authed request, and snapshotting
the Authorization + routing headers to disk. Subsequent CLI calls reuse
the cached headers from Node fetch without re-opening the browser.
Multiple resources (Outlook / Graph / Substrate)
Each Microsoft API is a separate OAuth resource with its own token audience;
a token is only valid against its own resource. resources.mjs is the
registry. Tokens are captured per-resource (captureAllTokens classifies
every Bearer OWA/Teams/Copilot emit by audience), cached per-resource
(auth-<resource>.json), and routed per-resource (call(auth, path, { resource }), getAuth({ resource })). outlook graph <path> is the generic
Graph passthrough; outlook token-audit reports what's reachable. Reaching
Teams/Copilot is a capture problem (get the right-audience token), not a
consent problem — see LEARNINGS.md §13. Non-default
resources never auto-launch the browser mid-command; they error toward auth --all.
TL;DR — hard constraints you must respect
- Never add OAuth flows that require admin consent. The whole point of
this project is to avoid them. Many corporate tenants block them. See
LEARNINGS.md§1–4. - Never assume headless Chromium will work. Microsoft Conditional Access
stalls silent SSO when the UA looks headless. We always launch headed.
See
LEARNINGS.md§10. - Never read tokens from the macOS keychain in Office identity slots.
They're ACL-protected to Microsoft-signed binaries; CLI tools just get
silent empty reads. See
LEARNINGS.md§5. - Never authenticate with cookies alone against the REST API. The
/api/v2.0/me/messagesendpoint returns 401 on cookie-only calls — it requires a Bearer token with audiencehttps://outlook.office.com/. - Don't commit anything from
~/.cache/outlook-spike/or~/.local/share/ outlook-spike/into the repo. These contain real credentials. The.gitignorealready protects against the obvious filenames; double-check anything you stage.
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.
- 3d ago First seen · 208 lines · 2,473 tokens per session scan A 64ad6d350c3b
outlook-cli AGENTS.md is an instructions file published in the GitHub repository muhammaddadu/outlook-cli (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,473 tokens to every session, about $0.0124 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 2026-08-31.
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).
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.
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.
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 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).
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.