gantry: Skill for Claude Code

.claude/skills/proxy-pipeline/SKILL.md

proxy-pipeline is a skill for Claude Code from geleynse/gantry. It costs 59 tokens per session (3,117 once invoked), scanned A, original, MIT.

A guide to Gantry's proxy pipeline, the shared sequence that handles agent tool requests before sending them to the game server. It explains guards, automatic actions, compound tools, and the difference between version-one and version-two requests.

In plain words
What is it for?
Adding or changing safety checks, response injections, waiting or enrichment behavior, tool dispatch, shared state, and configuration reload handling in the proxy.
Why use it?
It helps developers change request behavior in the shared implementation instead of fixing only one entry point and accidentally leaving another path inconsistent.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is geleynse/gantry's own configuration. It tells Claude Code how to work on gantry itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gantry configures →

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/proxy-pipeline/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.

agentmods badge for proxy-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/geleynse/gantry/proxy-pipeline/github.svg)](https://agentmods.dev/skills/geleynse/gantry/proxy-pipeline)
Your own site
<a href="https://agentmods.dev/skills/geleynse/gantry/proxy-pipeline"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/proxy-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for proxy-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/geleynse/gantry/proxy-pipeline"><img src="https://agentmods.dev/badge/skills/geleynse/gantry/proxy-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,117 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.03117
Opus 5.5 $0.00024 $0.01247
Sonnet 5.5 $0.00012 $0.00623
Haiku 4.5 $0.00006 $0.00312

Measured 2mo ago against content hash bcac11d79229, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

proxy-pipeline 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 2mo 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/proxy-pipeline/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proxy Request Pipeline — Gantry

Every agent tool call (v1 flat tool or v2 spacemolt(action=...)) flows through the same shared pipeline, implemented once in pipeline.ts / passthrough-handler.ts / injection-registry.ts and called from both server.ts (v1 factory) and gantry-v2.ts (v2 factory). Modify the shared functions, not the per-version factories, unless the behavior genuinely differs between v1 and v2.

Request flow

MCP tools/call (v1 or v2 endpoint)
  1. getAgentForSession()        pipeline.ts — session→agent lookup, restart recovery
  2. tool-name sanitization       gantry-v2.ts — strips XML artifact suffixes from action strings
  3. checkGuardrailsV1/V2()       pipeline.ts — see Guardrails below
  4. combat auto-trigger check    combat-auto-trigger.ts — substitutes flee/scan_and_attack on pirate_combat events
  5a. compound-tool dispatch      tool-registry.ts buildCompoundActions() dispatch table
  5b. OR passthrough              passthrough-handler.ts handlePassthrough()
        -> per-tool structural guards (fuel-floor, cargo-full-dock, refuel-target, pre-dock, ...)
        -> executeForClient()     dispatch-v1-to-v2.ts — routes v1 names to v2 {tool,action} when isV2()
        -> tick wait / event-buffer poll for STATE_CHANGING_TOOLS
        -> error hints            error-hints.ts addErrorHint()
  6. withInjections()             injection-registry.ts — merges all enabled injections
  7. decontaminateLog()           pipeline.ts + proxy-constants.ts CONTAMINATION_WORDS
  8. logToolCallStart/Complete()  tool-call-logger.ts — SQLite + ring buffer + SSE push
Agent receives result

docs/architecture.md's pipeline diagram lists 9 numbered stages in roughly this order — it does call out combat auto-trigger explicitly (its stage 4, "Pre-flight checks"), but it never mentions the structural per-tool guards (fuel-floor, cargo-full-dock, refuel-target, pre-dock) at all, in any stage — use the file list above as the authoritative map when you need to find where a specific behavior lives.

Read the full file on GitHub · 217 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. 2mo ago First seen · 217 lines · 59 tokens per session scan A bcac11d79229

Subscribe to this mod's changes

proxy-pipeline is a skill published in the GitHub repository geleynse/gantry (4 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 3,117 once invoked, about $0.0002 per session on Opus 5.5. 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

proxy-pipeline compared with skills from other repositories

proxy-pipeline next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
proxy-pipelinegeleynse/gantrySkill42mo agoMITA59Claude Code
mem0-oss-to-platformmem0ai/mem0Skill68k2d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2kyesterdayMITA46Claude Code
dev-runtimelangwatch/langwatchSkill5.0kyesterdayApache-2.0A172Claude Code
api-designericrisco/rsc-harnessSkill5032d agoMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill252yesterdayMITA106Claude Code