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.
npx skills add ai-analyst-lab/ai-analyst --skill pacegit clone --depth 1 https://github.com/ai-analyst-lab/ai-analystWrote 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.
[](https://agentmods.dev/skills/ai-analyst-lab/ai-analyst/pace)<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.
<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>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 5.1 | $0.00185 | $0.01351 |
| Opus 5 | $0.00093 | $0.00675 |
| Sonnet 5 | $0.00037 | $0.00270 |
| Haiku 4.5 | $0.00018 | $0.00135 |
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.
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
- Resolve the target mode. If the argument is one of
guided|narrated|autopilot, use it. If no argument, print the current mode (read fromworking/session_state.yaml→pace_mode) and the three options. Stop. - 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.
- Read existing state. Load
working/session_state.yamlif it exists; otherwise start with an empty dict. Preserve every other key. - Write atomically. Write the updated YAML to
working/session_state.yaml.tmp, then rename toworking/session_state.yaml. This prevents corruption if the process is interrupted mid-write. - 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."
- 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.
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.
- 2d ago First seen · 117 lines · 185 tokens per session scan A 61cd7bda0050
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.