What is configuration?

A guide to Gantry's configuration files and environment variables. It explains where settings are found, which values can reload while the server runs, and which are fixed at startup.

Editing gantry.json, adding or removing settings, selecting staging or other environments, tracing configuration lookup, and debugging hot-reload or startup behavior.

It helps explain why a configuration change was ignored and prevents mistakes with fleet directories, environment-specific files, paths, and secrets.

How geleynse/gantry configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to geleynse/gantry. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/geleynse/gantry/main/.claude/skills/configuration/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/geleynse/gantry

Made for: Claude Code.

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/geleynse/gantry/configuration.svg)](https://agentmods.dev/skills/geleynse/gantry/configuration)

Your own site

<a href="https://agentmods.dev/skills/geleynse/gantry/configuration"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/configuration.svg" alt="Measured on agentmods" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,605 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00046	$0.02605
Opus 5	$0.00023	$0.01303
Sonnet 5	$0.00009	$0.00521
Haiku 4.5	$0.00005	$0.00261

Measured 7d ago against content hash 15155eac229b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

configuration 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 7d 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.

.claude/skills/configuration/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configuration — Gantry Server

Two layers: gantry.json (fleet/agent settings, hot-reloaded) and environment variables (port, paths, secrets, set once at process start). Full field-by-field reference: docs/configuration.md. This skill covers the mechanics — resolution, reload, and the copy-block gotcha — that the reference doc doesn't.

Config file location

server/src/config/fleet.ts::resolveConfigPath(fleetDir) tries, in order, and uses the first that exists:

$FLEET_DIR/gantry.$GANTRY_ENV.json — only if GANTRY_ENV env var is set
$FLEET_DIR/gantry.json
$FLEET_DIR/fleet-config.json — backward-compat name

Throws with the full list of tried paths if none exist.

FLEET_DIR itself is resolved by server/src/config/env.ts::resolveFleetDir(), in order:

FLEET_DIR env var, if set — throws immediately if the directory doesn't exist (no fallback)
../fleet-agents relative to process.cwd() — the monorepo dev layout; used only if FLEET_DIR is unset
In tests (NODE_ENV=test or BUN_ENV=test): /dev/null placeholder — tests must call setConfigForTesting()
Otherwise: throws FLEET_DIR not configured

GANTRY_ENV=staging bun run dev   # loads $FLEET_DIR/gantry.staging.json

Hot-reload: what's live vs what's a snapshot

fleet.ts calls watchFile(configPath, { interval: 5000 }, ...) — polls the resolved config file every 5 seconds and re-parses on change via the same loadConfig() used at startup. On success it updates AGENTS, AGENT_NAMES, TURN_SLEEP_MS/TURN_INTERVAL and the module-level cachedConfig. On parse failure it logs and keeps serving the last good config — a bad edit doesn't crash the process.

Two ways code reads config, with different freshness:

getConfig() (config/fleet.ts) — always returns the current cachedConfig, i.e. picks up hot-reloaded values. Call sites that deliberately re-fetch this per-request for hot-reload support: agentDeniedTools deny checks, prayEnabled checks, routineMode checks, outbound.forum/outbound.chat policy lookups (all in proxy/gantry-v2.ts).
createGantryServerV2(config, shared, allowedTools?) (proxy/gantry-v2.ts) — takes config: GantryConfig as a parameter, captured once when the MCP server/session is created. Fields read only from this captured snapshot do not pick up a hot-reload without a new connection.

Read the full file on GitHub · 100 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.

7d ago First seen · 100 lines · 46 tokens per session scan A 15155eac229b

Subscribe to this mod's changes

configuration is a skill published in the GitHub repository geleynse/gantry (3 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 2,605 once invoked, about $0.0002 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.

DevOps and cloud

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

gantry: Skill for Claude Code