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 conorbronsdon/agent-workspace --skill updategit clone --depth 1 https://github.com/conorbronsdon/agent-workspaceWrote 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/conorbronsdon/agent-workspace/update)<a href="https://agentmods.dev/skills/conorbronsdon/agent-workspace/update"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-workspace/update/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/conorbronsdon/agent-workspace/update"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-workspace/update.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 | $0.00026 | $0.00399 |
| Opus 5.5 | $0.00010 | $0.00160 |
| Sonnet 5.5 | $0.00005 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
update 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 1mo 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.
What it actually says
/update — Quick Checkpoint
Save progress mid-session without closing. Fast and low-ceremony: a log line plus a state touch only if something actually changed.
Invocation: user-only (disable-model-invocation: true) — checkpoints are timed by
you, and the flag keeps this skill out of ambient context.
Configuration
Read the optional workspace.yaml at the project root. Below, <state_dir> and
<sessions_dir> are its resolved values; defaults are state/ and sessions/. Full
reference: docs/state-model.md.
Instructions
-
Scan recent conversation. Identify in ~30 seconds: what was worked on, any decisions made, any state changes needed.
-
Append to session log. Add to
<sessions_dir>/{TODAY}.md(create it if absent):## Update: {TIME} - {what was worked on, 1–3 bullets max} -
Update state only if something changed. Touch
<state_dir>/current.mdonly if a priority shifted, a thread opened or closed, or a task completed. Skip otherwise — an/updatewith no real change writes only the log line. -
Confirm. One line: "Checkpointed: {brief description}".
Design principles
- Fast. A checkpoint should cost seconds, not minutes.
- Skip what's clean. Don't rewrite
current.mdfor a checkpoint that changed nothing. - Standing rule. Whenever you run
/update, log first, then decide whether state actually moved — don't invent a state change to justify the run.
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.
- 1mo ago First seen · 44 lines · 26 tokens per session scan A b66a39500139
update is a skill published in the GitHub repository conorbronsdon/agent-workspace (2 stars, last pushed 26d ago), licensed MIT. It adds 26 tokens to every session and 399 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
context-bankruptcy
Declare bankruptcy on a long-lived AI agent's accumulated memory — audit what it currently believes, separate ground truth from stale and wrong, purge deliberately, restate the truths that survive, and log what was lost. Use when an agent keeps acting on outdated facts, contradicts itself across sessions, 'remembers'…
reminder
Set reminders and manage todos with natural language. Uses built-in cron scheduling, no external service needed.
daily-briefing
Daily briefing aggregating weather, reminders, news, and calendar. Delivered on schedule via any channel.
email-assistant
Read, search, draft, and send emails via Himalaya CLI or Python IMAP/SMTP. Requires email account configuration.
claude-reflect
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
calendar
Manage calendar events via CalDAV (Google/iCloud/Nextcloud) or local ICS files. View, create, and query events.