end-session

A read-only end-of-session checklist that reconstructs recent work and prepares documentation handoffs, issue synchronization, Kano refinement, and git checks.

In plain words
What is it for?
Use it when closing a maintainer session, classifying notes and decisions, preparing handoff blocks, reviewing issue updates, or checking git state.
Why use it?
It helps preserve useful decisions and evidence after a work session while keeping documents directed to the appropriate repository owners. It also checks repository hygiene without editing sibling repositories.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/lykhoyda/rn-dev-agent/end-session
Clone the repo
git clone --depth 1 https://github.com/Lykhoyda/rn-dev-agent

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,442 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00030 $0.01442
Opus 5 $0.00015 $0.00721
Sonnet 5 $0.00006 $0.00288
Haiku 4.5 $0.00003 $0.00144

Measured 2d ago against content hash ad95b8682729, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/end-session — session wrap-up

A maintainer ritual for this repository. It reconstructs the session, classifies durable knowledge by owner, and returns reviewable handoffs without writing to another repository.

Owner Canonical destination Content
rn-dev-agent-workspace Engineering docs Process, planning, routine engineering decisions, bugs, stories, specifications, diagnostics, comparisons, and research
Anton Factory architect-docs Captain-approved architecture vision, ADRs, authority contracts, settled decisions, evidence indexes, and architecture changelogs
rn-dev-agent apps/docs-site Public product and user documentation only

$ARGUMENTS is an explicit maintainer focus. Weave it into the reconstruction; it does not replace evidence gathering.

Iron rules

  1. Read other repositories; never write them. Produce exact handoff blocks and target links in the final report. Do not edit a sibling checkout, clone another repository, or add cross-repository automation.
  2. Never create top-level docs/ here. Engineering material belongs in the workspace; product documentation remains under apps/docs-site.
  3. Classify before drafting. Routine engineering and process decisions go to workspace docs. Only captain-approved, settled architecture goes to Anton Factory architect-docs. An unapproved proposal remains workspace planning material, never a Factory ADR.
  4. Use pointers across owners. A Factory architecture handoff links to workspace process evidence instead of copying its narrative. A workspace handoff links to any accepted Factory record instead of duplicating the architecture record.
  5. Never fabricate. Omit a handoff category when the session produced nothing that qualifies. Use today's date from date +%F and preserve the destination's established format and sequence when it can be read.
  6. GitHub mutation is gated. Creating issues and applying Kano labels are the only outward writes. Present the exact plan and wait for explicit maintainer confirmation.

Read the full file on GitHub · 136 lines

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. 2d ago First seen · 136 lines · 30 tokens per session scan A ad95b8682729

Subscribe to this mod's changes

end-session is a command published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,442 once invoked, about $0.0002 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.