pace

pace is a skill for Claude Code from ai-analyst-lab/ai-analyst. It costs 185 tokens per session (1,351 once invoked), scanned A, original, MIT.

A control for how visibly an analysis is carried out: step-by-step with pauses, narrated without pauses, or silently with only the final result. It applies to larger analyses rather than simple lookups.

In plain words
What is it for?
Use it to set guided, narrated, or autopilot behavior for complex analytical work.
Why use it?
It lets users choose between reviewing each phase and receiving a finished answer without progress messages.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Good fit Use it to set guided, narrated, or autopilot behavior for complex analytical work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ai-analyst-lab/ai-analyst/pace
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.

Any agent
npx skills add ai-analyst-lab/ai-analyst --skill pace
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pace

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/pace/github.svg)](https://agentmods.dev/skills/ai-analyst-lab/ai-analyst/pace)
Your own site
<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst/pace"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/pace/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pace

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst/pace"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst/pace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,351 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00185 $0.01351
Opus 5 $0.00093 $0.00675
Sonnet 5 $0.00037 $0.00270
Haiku 4.5 $0.00018 $0.00135

Measured 2d ago against content hash 61cd7bda0050, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

pace scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/pace/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Pace

Purpose

Persist the user's explicit choice of pace mode — how visibly the analytical machinery surfaces during L3+ analyses. Pace is orthogonal to complexity level (L1–L5). Level decides which agents run; pace decides how visible the work is.

Modes

Mode Behavior
guided Announce each phase, run it, pause and wait for /continue before the next phase
narrated Announce each phase, run it, announce the result, continue to the next phase without pausing (the safe default)
autopilot Silent end-to-end. No phase banners. The final message is the user's first look at the work: open with the outcome, then findings, then what is next, written for a reader who saw none of the run.

Invocation

The user types one of:

  • /pace guided
  • /pace narrated
  • /pace autopilot
  • /pace (no argument) — show the current mode and the three options
  • Natural language: "slow down, pause between steps" → guided; "just run it silently" → autopilot; "narrate but don't stop" → narrated

Behavior

  1. Resolve the target mode. If the argument is one of guided|narrated|autopilot, use it. If no argument, print the current mode (read from working/session_state.yamlpace_mode) and the three options. Stop.
  2. Validate. If the argument is anything else, echo the three valid modes and ask which one the user wants. Do NOT guess or silently fall back.
  3. Read existing state. Load working/session_state.yaml if it exists; otherwise start with an empty dict. Preserve every other key.
  4. Write atomically. Write the updated YAML to working/session_state.yaml.tmp, then rename to working/session_state.yaml. This prevents corruption if the process is interrupted mid-write.
  5. Confirm to the user. One line:
    • guided → "Pace set to guided. I'll pause after each phase and wait for /continue."
    • narrated → "Pace set to narrated. I'll announce each phase and run end-to-end."
    • autopilot → "Pace set to autopilot. I'll run silently and show you the final output."
  6. Apply on next phase boundary. If an analysis is already in flight, the new mode takes effect starting with the next phase. Tell the user so. Never switch mid-phase — it produces inconsistent banner state.

Read the full file on GitHub · 117 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 · 117 lines · 185 tokens per session scan A 61cd7bda0050

Subscribe to this mod's changes

pace is a skill published in the GitHub repository ai-analyst-lab/ai-analyst (298 stars, last pushed 3d ago), licensed MIT. It adds 185 tokens to every session and 1,351 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.

Related

Other skills, from other repositories