using-agentstack

A set of instructions for operating and troubleshooting AgentStack, a system that manages AI coding-agent tools, skills, secrets, permissions, and machine setup.

In plain words
What is it for?
Diagnose AgentStack projects, inspect available toolsets, manage secrets and policies, bootstrap a machine, and clean up older MCP configurations.
Why use it?
It helps you check what is configured, trusted, and currently connected before changing an AgentStack setup.

Skill for Claude CodeCodex

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/tarekkharsa/agentstack/using-agentstack
Any agent
npx skills add Tarekkharsa/agentstack --skill using-agentstack
Clone the repo
git clone --depth 1 https://github.com/Tarekkharsa/agentstack

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 926 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.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.00926
Opus 5 $0.00027 $0.00463
Sonnet 5 $0.00011 $0.00185
Haiku 4.5 $0.00005 $0.00093

Measured 3d ago against content hash a27857438298, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-agentstack 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.

crates/cli/catalog/skills/using-agentstack/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use AgentStack

Start with the state

Run agentstack status first. Use agentstack doctor only when status points to a problem or deeper verification is needed.

Read these facts separately:

  • locked: portable content is pinned; this does not mean a connection is live.
  • trusted: a human approved the current manifest and lock on this machine.
  • default toolset: what a trusted new agent connection opens automatically.
  • live toolset: a process-scoped connection that exists right now.
  • delivery: which capabilities are served live and which are written to files.

Follow the delivery decision

When status says skills or MCP servers are served live:

  • Do not run use, apply, or render-locally to make them appear.
  • Do not create .mcp.json, .claude/skills/, .agents/skills/, or similar capability folders.
  • Use the trusted default toolset. If several toolsets exist without a default, ask the user which one should be selected.
  • The connection already receives loadable skill names and one-line descriptions. Refresh or filter them with agentstack_list_loadable(query).
  • Load only a needed full body with agentstack_load(name, reason). The user does not need to say the skill name when its description clearly matches.
  • Discover proxied runtime tools and their schemas with tools_search only when the task needs one.

File-only CLIs and capability kinds are rendered automatically. An explicit render_locally override is a compatibility choice, not the normal live path.

Change the source of truth only

  • Change .agentstack/agentstack.toml, legacy agentstack.toml, or the personal library. Never hand-edit generated provider configuration.
  • Keep secret values out of manifests and libraries. Declare ${REF} and tell the user to run agentstack secret set REF on each machine.
  • After changing selected skills or servers, preview with agentstack lock. Use agentstack lock --write only with authorization.
  • Never run agentstack trust for the user. Show what changed and leave the consent action to the human.
  • Preview any write. Do not add --write unless the user explicitly authorized that AgentStack change.
  • Respect policy and guard refusals. Explain them; never retry around them.

Read the full file on GitHub · 88 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 3d ago First seen · 88 lines · 54 tokens per session scan A a27857438298

Subscribe to this mod's changes

using-agentstack is a skill published in the GitHub repository Tarekkharsa/agentstack (3 stars, last pushed 20d ago), licensed Apache-2.0. It adds 54 tokens to every session and 926 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

local-frontend-check

Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.

ascending-llc/jarvis-registry · 52 tokens

release-notes

Edit an existing GitHub release's body into the project's bilingual (English + Chinese) template format with a References section built from merged PRs. Use when 修改 release、整理发布说明、release notes、编辑 release 内容、发版后整理、edit release body.

samanhappy/mcphub · 58 tokens

new-feature-design

Design and document new features with GitHub issue, low-level design (LLD), expert review, and testing plan. Creates structured documentation in .scratchpad/ with issue spec, technical design with diagrams and pseudo-code, multi-persona expert review, and a testing plan covering functional (curl and…

agentic-community/mcp-gateway-registry · 118 tokens

release-notes

Create release notes for a new version tag. Gathers all commits, PRs, issues fixed, and breaking changes since a previous release. Creates the release notes markdown file, tags the repo, and pushes. Asks the user to confirm the base version to diff against.

agentic-community/mcp-gateway-registry · 59 tokens

create-milestone

Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.

agentic-community/mcp-gateway-registry · 64 tokens

pr-review

Review a GitHub pull request using multiple expert personas. Takes a PR URL as input, analyzes the changes, and generates comprehensive review feedback from different perspectives (Merge Specialist, Frontend, Backend, Security, DevOps, AI/Agent, SRE, Chief Architect).

agentic-community/mcp-gateway-registry · 57 tokens