backend-diagnostics

backend-diagnostics is a skill for Claude Code, Codex from halsyourpal422/Battenmark. It costs 0 tokens per session (426 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide for failures in the FreeCAD backend, the software component that performs CAD operations. It uses only the service’s public status, capability, and error information.

In plain words
What is it for?
It is for inspecting service health, checking available capabilities, retrying failed operations, choosing supported alternatives, and verifying that recovery worked.
Why use it?
It helps distinguish backend problems from ordinary modelling mistakes and provides a controlled recovery path.

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/halsyourpal422/battenmark/backend-diagnostics
Any agent
npx skills add halsyourpal422/Battenmark --skill backend-diagnostics
Clone the repo
git clone --depth 1 https://github.com/halsyourpal422/Battenmark

Made for: Claude Code, Codex.

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 backend-diagnostics

README.md
[![agentmods](https://agentmods.dev/badge/skills/halsyourpal422/battenmark/backend-diagnostics.svg)](https://agentmods.dev/skills/halsyourpal422/battenmark/backend-diagnostics)
Your own site
<a href="https://agentmods.dev/skills/halsyourpal422/battenmark/backend-diagnostics"><img src="https://agentmods.dev/badge/skills/halsyourpal422/battenmark/backend-diagnostics.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 426 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 5.1 $0.00000 $0.00426
Opus 5 $0.00000 $0.00213
Sonnet 5 $0.00000 $0.00085
Haiku 4.5 $0.00000 $0.00043

Measured 4d ago against content hash bce1b76017e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

backend-diagnostics 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 4d 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.

skills/backend-diagnostics/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FreeCAD / Backend Diagnostics

Purpose

Diagnose backend/FreeCAD worker failures using only public Battenmark status, capability, and structured-error surfaces. Never bypass the typed service layer.

Use when

  • Public operation returns backend-related structured error.
  • Need kernel_status or inspect_backend_capabilities.

Do not use when

  • Ordinary geometry/selector/constraint errors (use modelling skills).
  • Tempted to run FreeCAD Python or edit worker internals — forbidden.

Preconditions

  • REQUIRED: Operating through a public Battenmark client; stay inside the public contract.

Planning rules

  1. Structured error is primary evidence.
  2. Establish backend presence, roles, capabilities.
  3. Smallest recovery: retry → capability-aware alternative → supported restart → re-verify.
  4. Never call private FreeCAD modules or shell.
  1. REQUIRED — Record failing operation + full structured error.
  2. REQUIREDkernel_statusinspect_backend_capabilities.
  3. REQUIRED — Recover (retry / alternative / supported restart only).
  4. REQUIRED — Re-run minimal public verification.

Geometry / mechanical rules

Not applicable.

Verification gates

Status/capability called; recovery used only public operations; post-recovery public call succeeds or clear capability-backed unavailability explanation; no private FreeCAD/shell used.

Failure recovery

This skill is the recovery procedure. If public recovery fails, report status + error to user/operator. Do not patch the worker or invoke FreeCADCmd from the agent.

Outputs

Captured error, capability/kernel snapshots, recovery steps, post-recovery verification result.

Platform notes

FreeCAD is Tier-1 authoritative backend; JSCAD is preview only. Capability flags tell the truth. Discovery/install helpers are operator actions, not agent actions.

Examples

export_step timeout → kernel_status → inspect_backend_capabilities → supported restart if available → retry trivial op → retry export. Never "run FreeCADCmd yourself".

Read the full file on GitHub · 46 lines

Files

What ships with it

1 file 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. 4d ago First seen · 46 lines · 0 tokens per session scan A bce1b76017e8

Subscribe to this mod's changes

backend-diagnostics is a skill published in the GitHub repository halsyourpal422/Battenmark (0 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 426 tokens. 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.