MarkdownLLM: Command for Claude Code

.claude/commands/end-session.md

end-session is a command for Claude Code from JanoshMoshiri/MarkdownLLM. It costs 12 tokens per session (625 once invoked), scanned A, original, MIT.

A deliberate command for closing a work session while preserving useful decisions, unresolved tasks, and project history.

In plain words
What is it for?
It helps record insights, resolve or track contradictions, manage open tasks, validate their status, synchronize project records, and create a detailed Git commit.
Why use it?
It reduces the chance that important findings or unfinished work will be forgotten between sessions.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is JanoshMoshiri/MarkdownLLM's own configuration. It tells Claude Code how to work on MarkdownLLM itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything MarkdownLLM configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/JanoshMoshiri/MarkdownLLM/main/.claude/commands/end-session.md
Clone the repo
git clone --depth 1 https://github.com/JanoshMoshiri/MarkdownLLM

Made for: Claude Code.

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 end-session

README.md
[![agentmods](https://agentmods.dev/badge/commands/janoshmoshiri/markdownllm/end-session/github.svg)](https://agentmods.dev/commands/janoshmoshiri/markdownllm/end-session)
Your own site
<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.

agentmods 80×15 button for end-session

Your own site · 80×15
<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>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 625 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $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

Measured 29d ago against content hash 538f0b4eddea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.claude/commands/end-session.md · 42 lines

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:

  1. Scan this session for insights worth preserving → create type: insight things.
  2. 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 is mdllm reckon . --keep <id> --reason "…". Raise a cue for any reasoned-from thing you modified that no cue covers. The commit gate refuses the session-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.
  3. Detect contradictions introduced this session → create type: conflict things.
  4. Manage open-loop things — create/update a plan or work thing for new forward intent, move resolved ones to a terminal status (orient reads them; continuity.md is retired).
  5. Commit with a rich session-end: message — the commit is the backward record (no WORKLOG file; mdllm worklog prints an on-demand view of git when wanted).
  6. Report publication debt: run python {framework_root}/tools/mdllm.py estate-sync . --status and surface the result. Under literal git.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).

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. 29d ago Changed · +1 lines 538f0b4eddea
  2. 1mo ago Changed · +1 lines cf32e64f5b5f
  3. 1mo ago Changed · +4 lines 59226a6a9743
  4. 2mo ago First seen · 36 lines · 12 tokens per session scan A 46dbf286649d

Subscribe to this mod's changes

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.

Related

end-session compared with commands from other repositories

end-session next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
end-sessionJanoshMoshiri/MarkdownLLMCommand54d agoMITA12Claude Code
minutes-ideassilverstein/minutesCommand1.6kyesterdayMITA48Claude Code, OpenCode
learnReflexioAI/claude-smartCommand7913d agoApache-2.0A14Claude Code
memory-storeverygoodplugins/mcp-automemCommand66yesterdayMITA10Claude Code
analyze-contextRohiRIK/OpenLtmCommand298d agoMITA39Claude Code
cc-memoryTheLobbi/claudeCommand217d agoMITA0Claude Code
lians-recallLians-ai/LiansCommand175d agoApache-2.0A19Claude Code