A work procedure for changing a Rust command-line application, a program operated through typed terminal commands. It covers commands, MCP server features, transports, authentication, tests, dependencies, and related documentation.

Use it when adding or changing Rust CLI commands, MCP tools, connection methods, authentication, integrations, tests, dependencies, or CLI documentation.

It provides a consistent process for implementing and verifying changes across the CLI and its supporting files.

worker-cli — Skill by bierlingm

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/bierlingm/spikes/worker-cli

Any agent

npx skills add bierlingm/spikes --skill worker-cli

Clone the repo

git clone --depth 1 https://github.com/bierlingm/spikes

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,210 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.

Model	Per session	Once invoked
Fable 5	$0.00020	$0.02210
Opus 5	$0.00010	$0.01105
Sonnet 5	$0.00004	$0.00442
Haiku 4.5	$0.00002	$0.00221

Measured yesterday against content hash ddee26212444, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

worker-cli 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.

- `agent-browser` — REQUIRED when the feature includes an end-to-end widget-in-page flow (e.g., golden-path `spikes init` → `spikes inject` → widget POST to `https://spikes.sh/spikes` served via `widget-test-server`). Us

.factory/skills/worker-cli/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI Worker

NOTE: Startup and cleanup are handled by worker-base. This skill defines the WORK PROCEDURE.

When to Use This Skill

Features that modify the Rust CLI at ./cli/. This includes:

MCP server tools, transports, and modes (rmcp SDK)
CLI commands (init, config, inject, deploy cloudflare, shares, auth, usage, etc.)
Integration tests and unit tests
Dependency changes in Cargo.toml
CLI-adjacent docs / README / templates under ./ and ./docs/
Version bumps and git tag creation (when explicitly the feature goal)

Required Skills

tuistory — REQUIRED when implementing or verifying any interactive CLI prompt (stdin TTY). Invoke before driving prompts like spikes init's hosted/self-host selection or spikes deploy cloudflare's hosted-warning confirmation. Each tuistory session counts as one interactiveChecks entry in the handoff. Evidence requirement: for any feature that adds or modifies an interactive prompt, your handoff's verification.interactiveChecks MUST contain at least one entry per prompt branch (e.g., both the default and non-default answers) with the full action transcript. A handoff that lacks tuistory evidence for a prompt feature will be flagged as incomplete by scrutiny.
agent-browser — REQUIRED when the feature includes an end-to-end widget-in-page flow (e.g., golden-path spikes init → spikes inject → widget POST to https://spikes.sh/spikes served via widget-test-server). Use it to click the widget button, submit a test spike, and capture network logs for the live POST response. Do not substitute with curl when an assertion calls for a real browser interaction.

Work Procedure

Read the feature description thoroughly. Understand preconditions, expected behavior, and verification steps.
Understand current code. Read relevant source files in ./cli/src/. Key files:
- main.rs — Command routing (clap derive). MCP already wired.
- commands/mcp.rs — MCP server (SpikesService, DataSource, TransportMode, all 9 tools)
- commands/export.rs — Export formats (EXTEND with new variants)
- spike.rs — Data models (Spike, Rating, SpikeType, is_resolved())
- storage.rs — load_spikes() reads .spikes/feedback.jsonl
- error.rs — Error types
- Cargo.toml — Dependencies

Read the full file on GitHub · 132 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.

yesterday First seen · 132 lines · 20 tokens per session scan A ddee26212444

Subscribe to this mod's changes

worker-cli is a skill published in the GitHub repository bierlingm/spikes (1 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 2,210 once invoked, about $0.0001 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 2026-08-31.

Security Testing Writing and docs

systematic-debugging

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

obra/superpowers · 21 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

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

worker-cli