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 agentmods add commands/iannuttall/claude-sessions/session-startgit clone --depth 1 https://github.com/iannuttall/claude-sessionsWrote 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/commands/iannuttall/claude-sessions/session-start)<a href="https://agentmods.dev/commands/iannuttall/claude-sessions/session-start"><img src="https://agentmods.dev/badge/commands/iannuttall/claude-sessions/session-start.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00155 |
| Opus 5 | $0.00000 | $0.00077 |
| Sonnet 5 | $0.00000 | $0.00031 |
| Haiku 4.5 | $0.00000 | $0.00015 |
Grade A, and why
session-start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Start a new development session by creating a session file in .claude/sessions/ with the format YYYY-MM-DD-HHMM-$ARGUMENTS.md (or just YYYY-MM-DD-HHMM.md if no name provided).
The session file should begin with:
- Session name and timestamp as the title
- Session overview section with start time
- Goals section (ask user for goals if not clear)
- Empty progress section ready for updates
After creating the file, create or update .claude/sessions/.current-session to track the active session filename.
Confirm the session has started and remind the user they can:
- Update it with
/project:session-update - End it with
/project:session-end
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.
- 5d ago First seen · 13 lines · 0 tokens per session scan A fe107917c47d
session-start is a command published in the GitHub repository iannuttall/claude-sessions (1,207 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 155 tokens. 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 2026-08-30.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.