start

start is a skill for Claude Code, Codex from conorbronsdon/agent-workspace. It costs 35 tokens per session (767 once invoked), scanned A, original, MIT.

A session-start briefing that loads saved project state and summarizes recent changes, priorities, deadlines, and blockers.

In plain words
What is it for?
It is for beginning work in a repository, reviewing recent commits and session notes, checking state freshness, and identifying the next important tasks.
Why use it?
It reduces the time spent reconstructing where the previous work session ended.

Skill for Claude CodeCodex

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/conorbronsdon/agent-workspace/start
Any agent
npx skills add conorbronsdon/agent-workspace --skill start
Clone the repo
git clone --depth 1 https://github.com/conorbronsdon/agent-workspace

Made for: Claude Code, Codex.

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 start

README.md
[![agentmods](https://agentmods.dev/badge/skills/conorbronsdon/agent-workspace/start.svg)](https://agentmods.dev/skills/conorbronsdon/agent-workspace/start)
Your own site
<a href="https://agentmods.dev/skills/conorbronsdon/agent-workspace/start"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-workspace/start.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 767 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00767
Opus 5 $0.00017 $0.00383
Sonnet 5 $0.00007 $0.00153
Haiku 4.5 $0.00003 $0.00077

Measured 3d ago against content hash ab847b3851ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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 3d 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.

skills/start/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/start — Begin Session

Load your workspace state so the session begins where the last one left off, then give a short briefing. User-timed, so nothing runs ambiently.

Invocation: user-only (disable-model-invocation: true) — you decide when a session starts, and the flag keeps this skill out of ambient context.

Configuration

Read the optional workspace.yaml at the project root. Below, <state_dir>, <sessions_dir>, and <task_file> are its resolved values; defaults are state/, sessions/, and TODO.md. Staleness thresholds come from staleness.current_days (3), weekly_days (5), blockers_days (7). Full reference: docs/state-model.md.

Instructions

  1. Get today's date. Run date +%Y-%m-%d. Note the day of week.

  2. Check what changed since last session. If this is a git repository, find the most recent session log in <sessions_dir> and run:

    git log --oneline --since="<last session date>"
    

    Flag any state or context files modified since the last session — they may hold updates from other sessions or manual edits. If not a git repository (git rev-parse --git-dir fails), skip this step and continue.

  3. Load context (read in order):

    • <state_dir>/current.md — active priorities, open threads
    • <state_dir>/decisions.md — scan the last 5 entries for awareness
    • <state_dir>/weekly-priorities.md — what matters this week
    • <state_dir>/blockers.md — things waiting on dependencies
    • <sessions_dir>/{TODAY}.md — if it exists, you are resuming today
  4. Health checks. Flag anything that needs attention; skip silently if all clean:

    • current.md older than staleness.current_days — flag it
    • weekly-priorities.md older than staleness.weekly_days — flag it
    • blockers.md older than staleness.blockers_days — flag it
    • Inbox: if the project keeps a drop-zone (e.g. inbox/) and it holds files, note the count and suggest triaging them
    • Overdue items: scan <task_file> for unchecked items with a date that has passed

Read the full file on GitHub · 67 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. 3d ago First seen · 67 lines · 35 tokens per session scan A ab847b3851ad

Subscribe to this mod's changes

start is a skill published in the GitHub repository conorbronsdon/agent-workspace (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 767 once invoked, about $0.0002 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 2026-08-31.