A login procedure for dirctl, the command-line client used to access the AGNTCY Directory configured in dir-mcp. It uses a browser-based sign-in and stores a token for the server to use.

Use it to sign in to the configured AGNTCY Directory and make the resulting login available to dir-mcp.

It removes the need to manually create or copy an authentication token, while checking the approved client path before login.

dirctl-auth — Skill for Claude Code and Codex by agntcy: A login procedure for dirctl, the command-line client used…

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 skills/agntcy/dir-mcp/dirctl-auth

Any agent

npx skills add agntcy/dir-mcp --skill dirctl-auth

Clone the repo

git clone --depth 1 https://github.com/agntcy/dir-mcp

Made for: Claude Code, Codex.

Or install agntcy-dir, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/agntcy/dir-mcp/dirctl-auth.svg)](https://agentmods.dev/skills/agntcy/dir-mcp/dirctl-auth)

Your own site

<a href="https://agentmods.dev/skills/agntcy/dir-mcp/dirctl-auth"><img src="https://agentmods.dev/badge/skills/agntcy/dir-mcp/dirctl-auth.svg" alt="Measured on agentmods" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,866 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00092	$0.01866
Opus 5	$0.00046	$0.00933
Sonnet 5	$0.00018	$0.00373
Haiku 4.5	$0.00009	$0.00187

Measured today against content hash a9782d988b81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dirctl-auth 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.

dir-mcp-plugins/claude/skills/dirctl-auth/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authenticate with dirctl

Use this skill to log in to the AGNTCY Directory instance that dir-mcp is configured to use. It runs dirctl auth login which opens a browser-based PKCE flow and caches the resulting token for the MCP server to pick up automatically.

1. Invoke dirctl through the dir-mcp npm package — never system-wide

Never run a bare dirctl, which dirctl, or search the filesystem/PATH for the binary. The @agntcy/dir-mcp npm package — the same one .mcp.json runs via npx -y @agntcy/dir-mcp — exposes the platform-specific dirctl binary it already downloaded as a second bin entry. Invoke it through npx so you always get that binary, not a possibly-different one that happens to be installed elsewhere on the machine:

npx -y --package=@agntcy/dir-mcp dirctl <subcommand and flags>

Run this exact command (with subcommand/flags appended) in place of every dirctl invocation below — treat $DIRCTL in this doc's prose as shorthand for npx -y --package=@agntcy/dir-mcp dirctl, not as a shell variable to actually set. Do not assign it with VAR="..." first: that syntax is bash/zsh-only and fails outright under fish (fish: Unsupported use of '='), and you cannot assume which shell the Bash tool is running. Always spell out the full npx ... command in each call. Internally this wrapper (bin/dirctl.js in the package) already:

loads ~/.config/dir-mcp/config.json (or $DIR_MCP_CONFIG) and merges it under the process environment, so it picks up DIRECTORY_CLIENT_* settings automatically — you don't need to export them yourself;
resolves the actual binary from DIRECTORY_DIRCTL_PATH if that's set (config or env), otherwise from its own package bin/ directory — it never scans PATH or the rest of the filesystem;
chmods the binary executable if needed before spawning it.

If dirctl version (or any subcommand) fails with "dirctl binary not found", the platform download at install time failed — tell the user to re-run npx -y @agntcy/dir-mcp once, or reinstall the plugin, to restore it. Do not fall back to a system dirctl even if one is present.

Read the full file on GitHub · 117 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.

today Changed · +53 tokens per session a9782d988b81
4d ago First seen · 117 lines · 39 tokens per session scan A a742ee0be75f

Subscribe to this mod's changes

dirctl-auth is a skill published in the GitHub repository agntcy/dir-mcp (2 stars, last pushed today), licensed Apache-2.0. It adds 92 tokens to every session and 1,866 once invoked, about $0.0005 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.

Security

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens