Borrowing it
Nothing to install: this file belongs to puritysb/AgentDeck. 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/puritysb/AgentDeck/master/.agents/skills/session-end/SKILL.mdgit clone --depth 1 https://github.com/puritysb/AgentDeckWrote 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/puritysb/agentdeck/session-end)<a href="https://agentmods.dev/skills/puritysb/agentdeck/session-end"><img src="https://agentmods.dev/badge/skills/puritysb/agentdeck/session-end/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/skills/puritysb/agentdeck/session-end"><img src="https://agentmods.dev/badge/skills/puritysb/agentdeck/session-end.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.00782 |
| Opus 5.5 | $0.00029 | $0.00313 |
| Sonnet 5.5 | $0.00014 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
session-end 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 12d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session End
Use this skill at the end of a work session, before /clear, /new, switching tasks, or handing work to another Codex/Claude session. Its job is a handoff the next session can act on without the transcript. It does not create a record of everything that happened; git, the PRs and the issues already hold that.
1. Read the state (cheap commands only)
git status -sb
git worktree list
gh pr list --author @me --state open --json number,title,headRefName,mergeable
Do not read DEVELOPMENT_LOG.md or the devlog entries here. Nothing in the handoff depends on them.
2. Close out what this session started
- Uncommitted changes. Commit them on the task branch, or name them in the handoff as deliberately left uncommitted. Never revert, stash, or restore another session's changes in a shared tree.
- Worktrees this session created. Remove one only when its branch is pushed, its tree is clean, and no other session owns it (
AGENTS.md§ Agent working agreements). Otherwise list it with the reason it stays. - PRs this session opened. List each with its state: CI, mergeable, review, and what blocks it.
- Background agents or long commands. Say whether each is still running. Never report a result you have not received.
3. Record only what git cannot
| What you learned | Where it goes |
|---|---|
| A domain invariant (a rule future edits must keep) | the matching .claude/rules/<domain>.md. Move the rule body there verbatim; never paraphrase it |
| A measurement, incident, pitfall, or decision with its rejected alternatives | one new file docs/devlog/entries/YYYY-MM-DD-<slug>.md (line 1 # YYYY-MM-DD — title, ### sections, links relative to the repo root), committed with the change. Nothing to regenerate |
| A personal preference or dated retrieval hint | agent memory (local, not the repo) |
| What changed and why | nothing: the diff and the PR body already say it |
Update AGENTS.md only for a project-wide workflow or invariant change, and stay inside its byte budget (pnpm docs:check). Never write secrets, tokens, device passcodes, or raw transcripts into any of these.
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.
- 12d ago Changed · -1 lines · +11 tokens per session 6b1fbfc663ec
- 29d ago Changed · -1 lines db0054d02072
- 1mo ago Changed 520c577f80d7
- 1mo ago Changed ca76d169cc09
- 1mo ago First seen · 60 lines · 61 tokens per session scan A d754991aef8e
session-end is a skill published in the GitHub repository puritysb/AgentDeck (274 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 782 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
V3 Memory Unification
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).
nap
Reclaims context window budget by compressing agent histories, pruning old logs, archiving stale decisions, and cleaning orphaned inbox files.
memory-grounding
Recall past conversations, feelings, and diary entries for personal grounding.
remember
Store a persistent memory fact.
recall
Retrieve stored memories.