claude

A production Linux runtime image containing the Claude Code command-line program and the libraries and certificates it needs to run.

In plain words
What is it for?
Use it to build and validate Claude-based agent runs, with the executable selected locally or downloaded at a version and checksum specified by the project.
Why use it?
It provides a repeatable environment for testing Claude execution and Telegram gateway examples in production-like conditions.

Agent

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 agents/the-void-ia/void-box/claude
Clone the repo
git clone --depth 1 https://github.com/the-void-ia/void-box
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,099 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.01099
Opus 5 $0.00000 $0.00549
Sonnet 5 $0.00000 $0.00220
Haiku 4.5 $0.00000 $0.00110

Measured 2d ago against content hash f0e33aa29fd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

awk + curl + sha256sum/shasum are available.
docs/agents/claude.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude flavor — scripts/build_claude_rootfs.sh

Production Claude-capable rootfs/initramfs.

What it bundles

  • Native claude-code binary (Bun single-executable, glibc-linked).
  • Glibc shared libraries auto-detected via ldd.
  • SSL CA certificates for HTTPS API calls.
  • /etc/passwd + /etc/group for the sandbox user (uid 1000).
  • /usr/local/bin/claude symlink to claude-code.

When to use

  • Validating production-like Claude execution paths.
  • OpenClaw Telegram gateway example runs.

Discovery

The script locates the claude binary in priority order:

  1. CLAUDE_BIN env var pointing at a Linux ELF binary — local dev only.
  2. ~/.local/bin/claude or claude on PATH (Linux host only) — local dev only.
  3. CLAUDE_CODE_VERSION set → explicit override; requires a matching CLAUDE_CODE_SHA256 env var so developers supply the hash they are asking the build to trust.
  4. Default: download the version and URL pinned in scripts/agents/manifest.toml and verify against the pinned SHA-256.

Pinning and verification (R-B5c.1)

The default build path is hash-pinned. scripts/agents/manifest.toml holds one table per (agent, platform, arch) tuple with a version, url template, and sha256. build_claude_rootfs.sh fetches the URL, computes SHA-256, and fails the build if the digest does not match — the expected and observed digests are both printed on failure.

Parser choice: shell + awk (scripts/lib/agent_manifest.sh). No Python or Rust sidecar is required, which keeps the builder working anywhere bash + awk + curl + sha256sum/shasum are available.

Hash updates are reviewed PRs, not silent upstream events. The weekly workflow .github/workflows/bump-agents.yml (Mondays 09:00 UTC) checks for new upstream versions and opens one PR per agent containing the bumped arches, with per-arch SHA-256s listed in the PR body.

Batching note (pragmatic deviation from R-B5c.1): the spec text says "one PR per (agent, platform, arch) bump — not batched" alongside a bump-agents/<agent>-<version> branch name that cannot disambiguate two arches sharing a version. We honour the branch-name pattern and combine both arches of the same agent version into a single PR, because the arches ship in lockstep upstream and splitting them produces two PRs that must be merged atomically for the release pipeline to stay coherent. The PR body surfaces each arch's URL and SHA-256 on its own row so review is still granular. If one arch legitimately lags (partial-merge of a prior PR, security patch, or upstream arch skew), the weekly run bumps only the lagging arch and leaves the matching one alone — the job no longer asserts arch parity.

Read the full file on GitHub · 107 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. 2d ago First seen · 107 lines · 0 tokens per session scan A f0e33aa29fd4

Subscribe to this mod's changes

claude is an agent published in the GitHub repository the-void-ia/void-box (88 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,099 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

playwright-test-generator

Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…

SigNoz/signoz · 0 tokens

playwright-test-healer

Use this agent to debug and fix failing SigNoz E2E Playwright tests. Examples — Context: A spec is red. user: 'tests/e2e/tests/dashboards/list.spec.ts is failing, fix it' assistant: 'Using the healer agent to debug each failing scenario and adjust the spec.' Context: After a frontend change a previously-green spec…

SigNoz/signoz · 0 tokens

playwright-test-planner

Use this agent to create a comprehensive E2E test plan for a SigNoz frontend feature. Examples — Context: A new feature has shipped and we need test coverage. user: 'Plan E2E tests for the alerts list page' assistant: 'I'll use the planner agent to read the relevant frontend source, navigate the page in a real…

SigNoz/signoz · 0 tokens

trace-analyzer

Analyze trace files for cases using agent-based detection.

Not-Diamond/self-care · 9 tokens

self-care/context-refiner

You are a context remediation agent for the Self-Care plugin. Your job is to propose and apply fixes for agent cases by editing project files — system prompts, tool descriptions, and context documents.

Not-Diamond/self-care · 5 tokens

build-and-dev-conventions

See AGENTS.md for the full command reference and developer quick-start. This document explains the architectural choices behind those commands.

kiali/kiali · 0 tokens