Borrowing it
Nothing to install: this file belongs to JanoshMoshiri/MarkdownLLM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JanoshMoshiri/MarkdownLLM/main/.claude/commands/end-session.mdgit clone --depth 1 https://github.com/JanoshMoshiri/MarkdownLLMWrote 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/janoshmoshiri/markdownllm/end-session)<a href="https://agentmods.dev/commands/janoshmoshiri/markdownllm/end-session"><img src="https://agentmods.dev/badge/commands/janoshmoshiri/markdownllm/end-session/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/commands/janoshmoshiri/markdownllm/end-session"><img src="https://agentmods.dev/badge/commands/janoshmoshiri/markdownllm/end-session.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 | $0.00012 | $0.00625 |
| Opus 5.5 | $0.00005 | $0.00250 |
| Sonnet 5.5 | $0.00002 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00063 |
Grade A, and why
end-session 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 29d 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
Run the session-end continuity ritual for this domain — and only because the
operator chose to end here. This is deliberate by design: insights are harvested
when you judge the session worth it, never automatically. Follow
{framework_root}/templates/prompts/session-end-continuity.md:
- Scan this session for insights worth preserving → create
type: insightthings. - The close — reckon what the workspace carries (the brake): run
python {framework_root}/tools/mdllm.py reckon . --close --apply. The floor applies the mechanical band and lists what this close owes, oldest first: the residue (at most four) goes to the operator in one native choice prompt, not now among the options and recorded as a hold; the settled items you decide by citing the record — insights: promote, dismiss, consolidate, link or hold; conflicts: rule, link or hold; cues: walk or answer by citation; fired triggers: act, re-date or disarm; work: start, unblock, pause or hold; workflows: write or bind. A hold ismdllm reckon . --keep <id> --reason "…". Raise a cue for any reasoned-from thing you modified that no cue covers. The commit gate refuses thesession-end:commit until the close is met — ten decisions today while a backlog stands, or the band emptied; an unattended session applies the mechanical band and drafts the rest, never answers. - Detect contradictions introduced this session → create
type: conflictthings. - Manage open-loop things — create/update a
planor work thing for new forward intent, move resolved ones to a terminal status (orient reads them;continuity.mdis retired). - Commit with a rich
session-end:message — the commit is the backward record (no WORKLOG file;mdllm worklogprints an on-demand view of git when wanted). - Report publication debt: run
python {framework_root}/tools/mdllm.py estate-sync . --statusand surface the result. Under literalgit.autopush: true,ahead +n (unpushed)is an anomaly — an offline session or rejected push owed a routing decision. Under false, absent, or malformed policy it is expected debt awaiting a human-authorized push. Route each line; never resolve a rejection by force and never infer send authority from silence (git-workflow.md → The Outbound Rules;autopush-requires-explicit-authority).
If the session has no domain-relevant changes worth harvesting, say so and stop — not every session earns an insight (publication debt still gets reported: step 6 reads git, not the session).
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.
- 29d ago Changed · +1 lines 538f0b4eddea
- 1mo ago Changed · +1 lines cf32e64f5b5f
- 1mo ago Changed · +4 lines 59226a6a9743
- 2mo ago First seen · 36 lines · 12 tokens per session scan A 46dbf286649d
end-session is a command published in the GitHub repository JanoshMoshiri/MarkdownLLM (5 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 625 once invoked, about $0.0000 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.
end-session compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| end-sessionJanoshMoshiri/MarkdownLLM | Command | 5 | 4d ago | MIT | A | 12 | Claude Code |
| minutes-ideassilverstein/minutes | Command | 1.6k | yesterday | MIT | A | 48 | Claude Code, OpenCode |
| learnReflexioAI/claude-smart | Command | 791 | 3d ago | Apache-2.0 | A | 14 | Claude Code |
| memory-storeverygoodplugins/mcp-automem | Command | 66 | yesterday | MIT | A | 10 | Claude Code |
| analyze-contextRohiRIK/OpenLtm | Command | 29 | 8d ago | MIT | A | 39 | Claude Code |
| cc-memoryTheLobbi/claude | Command | 21 | 7d ago | MIT | A | 0 | Claude Code |
| lians-recallLians-ai/Lians | Command | 17 | 5d ago | Apache-2.0 | A | 19 | Claude Code |