Process

What it does

When your agent uses it

• Tasks that involve Subagents
• Tasks that involve Retrospectives
• Tasks that involve Session handoff

Example prompts

• “/process”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob, Task, Agent

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1SETUP
2. 2EXECUTE (per task)
3. 3FINALIZE

What it can do on your machine

Read from SKILL.md and the folder at commit 5218674. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash
  • Grep
  • Glob
  • Task
  • Agent

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git
  • python3
  • gh

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git and gh, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Process loads about 2.1k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 30 tokens; SKILL.md has 843 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~30

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~10k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Bash, Grep, Glob, Task, Agent

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from notque/vexjoy-agent at commit 5218674, republished under its MIT licence (© notque). 843 words, ~2,099 tokens.

name

process

description

Process: retrospectives, session handoff, pair programming, subagent-driven development, condition-based waiting.

allowed-tools

Read, Write, Edit, Bash, Grep, Glob, Task, Agent

user-invocable

true

argument-hint

[retro|handoff|pair|subagent|wait]

routing.not_for

multi-phase feature work (use workflow), code review (use review)

routing.triggers

what didn't work, negative results, route health, routing telemetry, review roi, hand off this session, package session state, session pickup, rehydrate…

routing.category

process

routing.pairs_with

workflow, testing, pr-workflow

start = time.monotonic()
while time.monotonic() < start + timeout:
    if condition():
        return result
    time.sleep(interval)
raise TimeoutError(f"Timeout waiting for: {description}")

for attempt in range(max_retries + 1):
    try:
        return operation()
    except retryable_exceptions:
        if attempt >= max_retries: raise
        jitter = 1.0 + random.uniform(-0.5, 0.5)
        time.sleep(min(delay * jitter, max_delay))
        delay = min(delay * backoff_factor, max_delay)

© notque, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in skills/process/process of notque/vexjoy-agent.

• SKILL.md
• adr-reviewer-prompt.md
• code-quality-reviewer-prompt.md
• implementer-prompt.md
• references/cbw-implementation-patterns.md
• references/cbw-preferred-patterns.md
• references/cbw-testing-patterns.md

Open the folder on GitHubat commit 5218674