Pace

What it does

When your agent uses it

• The user invokes /pace
• /pace autopilot
• Says things like slow down and walk me through
• Pause between steps

Example prompts

• “slow down and walk me through”
• “pause between steps”
• “just run it silently”
• “/pace”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Resolve the target mode. If the argument is one of guided|narrated|autopilot,
2. 2Validate. If the argument is anything else, echo the three valid modes
3. 3Read existing state. Load working/session_state.yaml if it exists;
4. 4Write atomically. Write the updated YAML to
5. 5Confirm to the user. One line
6. 6Apply on next phase boundary. If an analysis is already in flight, the

What it can do on your machine

Read from SKILL.md and the folder at commit 52c0744. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

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

• Network

  No URLs in SKILL.md.

  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

Pace loads about 1.4k tokens when it runs. Until then it costs about 212 tokens; SKILL.md has 512 words of instructions outside code blocks.

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

~212

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

~1.4k

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

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 ai-analyst-lab/ai-analyst at commit 52c0744, republished under its MIT licence (© ai-analyst-lab). 512 words, ~1,373 tokens.

name

pace

description

Change how visibly Claude surfaces analytical work during L3+ analyses. Three modes — guided (announce each phase and pause for /continue), narrated (announce each phase and run end-to-end), autopilot (silent end-to-end, final output only). Use this skill whenever the user invokes `/pace`, `/pace guided`, `/pace narrated`, `/pace autopilot`, or says things like "slow down and walk me through", "pause between steps", "just run it silently", "narrate each step", "don't stop to ask me", "stop narrating". Pace is orthogonal to complexity level — it changes surfacing, not which agents run. Full spec and phase-banner format live in the question-router skill. This skill is the write-side: it persists the user's explicit pace choice to `working/session_state.yaml` so it survives across phases, across `/resume-pipeline`, and across sessions.

import yaml, os, pathlib, datetime

STATE_PATH = pathlib.Path("working/session_state.yaml")

def set_pace(mode: str) -> tuple[bool, str]:
    assert mode in {"guided", "narrated", "autopilot"}
    STATE_PATH.parent.mkdir(parents=True, exist_ok=True)

    state = {}
    if STATE_PATH.exists():
        try:
            state = yaml.safe_load(STATE_PATH.read_text()) or {}
        except yaml.YAMLError:
            bak = STATE_PATH.with_suffix(
                f".yaml.broken-{datetime.datetime.now().strftime('%Y%m%dT%H%M%S')}"
            )
            STATE_PATH.rename(bak)
            state = {}

    state["pace_mode"] = mode
    tmp = STATE_PATH.with_suffix(".yaml.tmp")
    try:
        tmp.write_text(yaml.safe_dump(state, sort_keys=False))
        os.replace(tmp, STATE_PATH)
        return True, ""
    except OSError as e:
        return False, str(e)

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

Files

Just SKILL.md in .claude/skills/pace of ai-analyst-lab/ai-analyst.

Open the folder on GitHubat commit 52c0744