agent-probe-dev

Development guidance for a Go program that runs on routers and servers, checks local gateway services, and sends reports to a collector over HTTP. It covers the program's layout, service scripts, protocol versions, and supported router constraints.

In plain words
What is it for?
Use it when changing anything in apps/agent, including the main loop, gateway clients, configuration, service wrapper, installer, or report and heartbeat requests.
Why use it?
It keeps changes consistent with the agent's communication protocol and limited router environments. It also provides checks to catch Go and shell-script problems before release.

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/foru17/neko-master/agent-probe-dev
Any agent
npx skills add foru17/neko-master --skill agent-probe-dev
Clone the repo
git clone --depth 1 https://github.com/foru17/neko-master

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 739 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 $0.00055 $0.00739
Opus 5 $0.00028 $0.00369
Sonnet 5 $0.00011 $0.00148
Haiku 4.5 $0.00006 $0.00074

Measured yesterday against content hash b89db036c1fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-probe-dev 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 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.

Makes network callslowCapability

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

- `install.sh` — curl-pipe installer
.claude/skills/agent-probe-dev/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Probe Development (apps/agent)

The agent is a Go binary deployed on routers/servers. It polls the local gateway (mihomo/Surge) and reports to the collector over HTTP (gzip JSON POST to /api/agent/report|heartbeat|config|policy-state) — not WebSocket.

Layout

  • main.go — entrypoint, flag parsing
  • internal/agent/runner.go — main loop: report/heartbeat/config-sync tickers, pending queue, retry batch
  • internal/gateway/ — mihomo & Surge API clients
  • internal/config/config.go — flags, AgentProtocolVersion
  • nekoagent — POSIX-sh service manager wrapper (install/upgrade/systemd/procd/launchd)
  • install.sh — curl-pipe installer

Verify

cd apps/agent
go vet ./... && go build ./... && go test ./...
sh -n nekoagent && sh -n install.sh   # shell syntax gate — both scripts must parse with POSIX sh

Hard rules

  1. Protocol versioning. Payload shape changes require bumping AgentProtocolVersion (Go) AND the collector's minimum accepted version (agent auth in apps/collector/src/modules/app/app.ts); the collector rejects too-old agents with HTTP 426 + structured error. The Go structs and the collector's TS payload types are mirrored by hand — change both sides in one commit.
  2. Data-loss protections are contracts: single in-flight retry batch, requestId idempotency dedup, counter-regression handling (gateway restart counts current value as new traffic), bounded pending queue with dropped accounting. Don't weaken these when refactoring the loop.
  3. Router constraints. Target environments include OpenWrt/BusyBox: nekoagent must stay POSIX sh (no bashisms), /tmp is tmpfs (RAM) — clean up temp dirs (accumulate EXIT traps, don't overwrite them), and network calls in shell must carry timeouts + retries (curl --connect-timeout 10 --max-time 120 --retry 3).
  4. Self-replacement. Never overwrite a running script/binary in place — download to a sibling .tmp/.new path and mv (same-filesystem rename) so the running inode survives.
  5. Service management. systemd unit: StartLimitIntervalSec/Burst belong in [Unit], not [Service]. procd (OpenWrt) respawn has a finite retry budget — treat "cannot start" as exit non-zero so supervisors behave correctly.

Read the full file on GitHub · 40 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 · 40 lines · 55 tokens per session scan A b89db036c1fb

Subscribe to this mod's changes

agent-probe-dev is a skill published in the GitHub repository foru17/neko-master (3,849 stars, last pushed 29d ago), licensed MIT. It adds 55 tokens to every session and 739 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories

data-viz-renderer

Generate self-contained HTML/SVG infographics from JSON data, including stat cards, bar charts, flow diagrams, and mixed dashboards. Offers 8 color palettes and built-in icons with no external dependencies. Triggered when users request data visualization, infographics, charts, or dashboards.

zebbern/claude-code-guide · 62 tokens

grafana-dashboard

Create, view, and manage Grafana dashboards with panels and datasources.

Datus-ai/Datus-agent · 18 tokens

superset-dashboard

Create, view, and manage Superset dashboards with charts and datasets.

Datus-ai/Datus-agent · 17 tokens

chart-designer

Design effective data visualizations and charts. Generate chart configurations for ECharts, Chart.js, and other libraries. Create dashboards and reports.

claude-office-skills/skills · 31 tokens

html-report

Parse data files of many formats — CSV/TSV, Excel (.xlsx), SQLite, JSONL/NDJSON, JSON, Markdown, plain text, and log files — and generate a stunning, self-contained, single-file HTML experience that visualizes the data: a Three.js animated hero, GSAP scroll animations, Tailwind styling, column-profiled data tables…

costiash/eliviz · 276 tokens

infographic

Turn a data file (CSV/TSV, Excel, SQLite, JSON/JSONL, Markdown, text, logs) into a static, shareable infographic IMAGE — a rendered PNG plus its editable HTML source. Composes real infographics (hero stat, numbered story spine, pictograms, annotations, takeaway), not styled dashboards. Use this skill whenever the user…

costiash/eliviz · 179 tokens