config

A guided command for changing non-secret settings for the team-management system.

In plain words
What is it for?
Use it to view current settings and update supported configuration values through a guided menu.
Why use it?
It helps users review and update configuration without putting API tokens or other secrets into the command session.

Command

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 commands/teammanagementplugin/claude-plugin/config
Clone the repo
git clone --depth 1 https://github.com/TeamManagementPlugin/claude-plugin
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,323 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 $0.00012 $0.02323
Opus 5 $0.00006 $0.01162
Sonnet 5 $0.00002 $0.00465
Haiku 4.5 $0.00001 $0.00232

Measured yesterday against content hash aaa9eb9c0fa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

config 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 yesterday.

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.

plugin/commands/config.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

team-management: Configure

Guide the user through team-management's non-secret configuration and write it with the deterministic config_update MCP tool. Secrets (API tokens) are NEVER set here — they live in the per-project file .claude/state/provider-tokens.json, which the AI cannot read, and never enter this transcript.

By the time this command runs, the deterministic intent-gate hook has already written the config session flag (you physically typed the command), so config_update is unlocked for ~15 minutes. Do NOT pre-authorize config_update — approve each write when prompted; the per-section batching keeps that to a handful of prompts.

Workflow

  1. Show current settings. Call mcp__plugin_team-management_tm__config_get and summarise the current config to the user. Token fields appear masked (***set*** / ***unset***) — that is expected; never ask the user to paste a token here. The response also carries a schema array — the authoritative list of every settable key with its type, any allowed enum values, and a one-line description. Treat it as ground truth: consult it for a key's exact type/enum before every config_update call rather than guessing, and never try to set a key absent from schema (those are either secrets — set in the token file — or engine-managed state).

  2. State the token-redirect up front:

    Tokens (GitLab / Jira / GitHub / Telegram) are NOT configured here. Set them in the per-project file .claude/state/provider-tokens.json — a git-ignored, owner-only (0600) file the AI agent cannot read. It is created for you (with all provider keys blank) the first time you run /team-management:config or start a session; open it in your editor and fill in only the tokens you use. Each project has its own file, so different projects can use different tokens.

  3. Walk the sections in order, one AskUserQuestion at a time. For each section, first ask whether the user wants to configure it (offer a clear "skip — leave as-is" option). Skip if not needed. When they do want it, gather the section's values with AskUserQuestion, then make ONE config_update call for the whole section (batched dotted keys — not one call per field). Section order:

Read the full file on GitHub · 154 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.

  1. yesterday First seen · 154 lines · 12 tokens per session scan A aaa9eb9c0fa9

Subscribe to this mod's changes

config is a command published in the GitHub repository TeamManagementPlugin/claude-plugin (4 stars, last pushed 26d ago), licensed MIT. It adds 12 tokens to every session and 2,323 once invoked, about $0.0001 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.