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 skills/anombyte93/atlas-session-lifecycle/stopnpx skills add anombyte93/atlas-session-lifecycle --skill stopgit clone --depth 1 https://github.com/anombyte93/atlas-session-lifecycleWrote 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/anombyte93/atlas-session-lifecycle/stop)<a href="https://agentmods.dev/skills/anombyte93/atlas-session-lifecycle/stop"><img src="https://agentmods.dev/badge/skills/anombyte93/atlas-session-lifecycle/stop.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 | $0.00059 | $0.01480 |
| Opus 5 | $0.00030 | $0.00740 |
| Sonnet 5 | $0.00012 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
stop 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 4d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Stop Skill
Graceful session close, pause, or verification. Three intents: Pause | Finish | Verify.
All session operations use atlas-session MCP tools directly (prefixed session_* and contract_*). Use ToolSearch to discover them.
Hard Invariants
- User authority is absolute — AI NEVER closes without confirmation.
- Human-visible memory only — All state lives in files.
- Trust separation — for bounty verify, spawn a separate finality Task agent. Never the same agent that submits.
- AtlasCoin is optional — if down, skip bounty steps and continue.
- Idempotent — Running /stop on an already-closed session exits cleanly.
- Archive after verification — Soul purpose is archived AFTER bounty settlement, not before.
UX Contract
- User sees ONE intent question, then results. Nothing else.
- No step announcements, no narration, no internal process descriptions.
Phase 0: Sync + State Detection
First, save the current session state so context files are up to date:
- Invoke
/sync— updates all session-context files and MEMORY.md with current progress. Silent, no output shown.
Then detect state:
- Call
session_read_context(project_dir)— get soul purpose, status hint, open tasks. - If
status_hintisno_purposeor soul purpose is empty: tell user "No active soul purpose to close." EXIT. - Check bounty: if
session-context/BOUNTY_ID.txtexists, callcontract_get_status(project_dir). StoreHAS_BOUNTY.
Phase 1: Intent Question
Ask ONE question via AskUserQuestion:
Question: "Soul purpose: '[soul purpose text]'. What would you like to do?"
- "Pause for the day" — Save state, keep purpose active.
- "Finished — verify and close" — Full settlement + PR + archive.
- "Just verify" — Check status, show results, return to work.
- "Cancel" — Do nothing. EXIT.
Store the user's choice as INTENT.
Read custom.md if it exists, follow instructions under "During Settlement".
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.
- 4d ago First seen · 163 lines · 59 tokens per session scan A aadfef4b6680
stop is a skill published in the GitHub repository anombyte93/atlas-session-lifecycle (88 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,480 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
session-orchestrator
Session orchestrator on top of the recall index of all Claude Code sessions: finds a past session by task description, dives in (context, project, skill, artifacts) and acts in one of three modes — finish here, hand off the resume command, or open the session in a new terminal window. Use when user asks: "find the…
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
trellis-session-insight
Reach into past AI conversation history through the trellis mem CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work…
trellis-channel
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.