source-command-end-session

An end-of-session command for a codebase: it checks the project, writes a handoff note, and records a Journal entry.

In plain words
What is it for?
It helps run the repository close-check, save session handoff details, record the session in the Journal, and surface loose threads.
Why use it?
It gathers unfinished work and verification warnings in one closing routine, so the next session can understand the project state.

Skill for Claude CodeCodex

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 skills/strale-io/strale/source-command-end-session
Any agent
npx skills add strale-io/strale --skill source-command-end-session
Clone the repo
git clone --depth 1 https://github.com/strale-io/strale

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,613 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 $0.01613
Opus 5 $0.00015 $0.00807
Sonnet 5 $0.00006 $0.00323
Haiku 4.5 $0.00003 $0.00161

Measured 2d ago against content hash f371bce86d24, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

source-command-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.

.agents/skills/source-command-end-session/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

source-command-end-session

Use this skill when the user asks to run the migrated source command end-session.

Command Template

/end-session — verify, then write session artifacts + surface loose threads

Purpose: complete CLAUDE.md's Quick Session Checklist on Petter's behalf (AGENTS.md → "Session Checklists" carries the Codex-flavored pointer to the same list — AGENTS.md has no numbered checklist of its own, CLAUDE.md's is canonical). This command DOES write the handoff file and Journal entry — that's the standing preference (set 2026-04-27). It still does not create Decisions DB entries, To-do mutations, or other governance artifacts without explicit per-item approval.

Run these steps in order. After the checks, write the artifacts (steps 2 and 3) before producing the final report.

1. Run the codebase close-check script

cd apps/api && npx tsx --env-file=../../.env scripts/session-close-check.ts

Checks git integrity, DB↔code parity, stuck caps, open breakers, uncommitted handoff files. Exit codes: 0 clean, 1 warnings, 2 blockers. Capture findings for the final report.

2. Write the session handoff file (CLAUDE.md Quick Session Checklist step 7)

Author a handoff file at handoff/_general/from-code/YYYY-MM-DD-<topic>.md covering this session's work. Convention:

  • First line is Intent: summarizing what the session set out to do.
  • Body covers what shipped, what's open, non-obvious learnings, and cost (if any).
  • Topic slug should be specific enough that future-you can grep for it (e.g. x402scan-indexing-and-pr-cleanup, not cleanup).

If a handoff file authored this session already exists for today's topic (e.g. an earlier /go invocation already wrote one), don't duplicate — report its path. Only one handoff per topic per day; if the session covered two distinct topics, write two files.

If the session was genuinely trivial (single trivial fix, nothing worth recording), still write a one-line handoff. Skipping is Petter's call, not yours.

Read the full file on GitHub · 119 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 · 119 lines · 30 tokens per session scan A f371bce86d24

Subscribe to this mod's changes

source-command-end-session is a skill published in the GitHub repository strale-io/strale (4 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,613 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 2026-08-31.

Related

Other skills, from other repositories

jentic-api-improve

Improve OpenAPI documents for AI-readiness by fixing issues and enriching content based on Jentic API AI-Readiness Framework (JAIRF) scoring. Use when you need to raise an API's quality score, fix diagnostics, or add missing descriptions/summaries/examples — whether directly requested ('improve my API', 'fix OpenAPI…

jentic/jentic-api-scorecard · 124 tokens

sdd-implement-spec

Implement an existing feature spec end-to-end — pick an unprocessed feature spec (one whose ## Phase N — ... heading in specs/roadmap.md does not yet carry the ✅ lifecycle marker), cut a feature branch, walk plan.md task groups in order with one primary atomic Conventional-Commits commit per group (plus optional small…

jentic/jentic-api-scorecard · 215 tokens

sdd-new-spec

Scaffold a feature spec for a roadmap phase and open it as a PR for human review. Reads specs/roadmap.md, lets the user pick a phase (or accepts one as argument), runs preflight checks, cuts a feature branch, writes specs/YYYY-MM-DD- / (requirements.md, plan.md, validation.md — grounded in specs/mission.md and…

jentic/jentic-api-scorecard · 141 tokens

sdd-new-phase

Append a new active phase to specs/roadmap.md. Parses existing phases (active and ✅-completed) to compute the next stable phase number per the lifecycle rule, grounds the proposal against specs/mission.md and specs/tech-stack.md, groups structured questions (goal, dependencies, priority) via AskUserQuestion, then…

jentic/jentic-api-scorecard · 137 tokens

sdd-distill-lessons

Distil per-spec retrospectives into specs/lessons.md so future spec authoring absorbs the learning. Reads specs//retrospective.md, groups recurring patterns, surfaces candidate lessons and tech-stack.md promotion candidates via AskUserQuestion, writes confirmed additions to specs/lessons.md, then invokes /review…

jentic/jentic-api-scorecard · 76 tokens

jentic-api-scorecard

Use the @jentic/api-scorecard-cli to score an OpenAPI document against the Jentic API AI Readiness Framework (JAIRF). Use this skill whenever the user wants to score, grade, lint, or assess the AI-readiness / agent-readiness / quality of an OpenAPI (Swagger) spec — by local file or URL — or asks how to run the…

jentic/jentic-api-scorecard · 121 tokens