shipkit-work-memory

A session-progress and resume system that records milestones, decisions, blockers, and the point where work should continue.

In plain words
What is it for?
It helps create or update .shipkit/progress.json using conversation details and, when available, Git changes.
Why use it?
It preserves useful project context between work sessions instead of relying only on memory or a brief conversation summary.

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/stefan-stepzero/shipkit/shipkit-work-memory
Any agent
npx skills add stefan-stepzero/shipkit --skill shipkit-work-memory
Clone the repo
git clone --depth 1 https://github.com/stefan-stepzero/shipkit

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,821 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 $0.00042 $0.02821
Opus 5 $0.00021 $0.01411
Sonnet 5 $0.00008 $0.00564
Haiku 4.5 $0.00004 $0.00282

Measured yesterday against content hash f4971b6c3321, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-work-memory 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 yesterday.

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.

install/skills/shipkit-work-memory/SKILL.md · 420 lines

How it starts

The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-work-memory - Session Progress & Resume State

Purpose: Capture structured session progress — milestones, blockers, decisions, and resume state — by inferring from conversation and git. User confirms, Claude does the work.

Note: Claude Code's auto-memory (v2.1.59+) automatically saves basic session context. This skill is for structured progress tracking that auto-memory doesn't capture: explicit milestones, decision rationale, blocker status, and handoff state for session continuity.

Output: .shipkit/progress.json — A timeline graph artifact ideal for session history visualization.


When to Invoke

User triggers:

  • "End session"
  • "Log progress"
  • "Save checkpoint"
  • "What did we do?"
  • "Save session"

Suggested after:

  • Long implementation sessions
  • Before context gets full
  • Before switching tasks
  • End of work session

Prerequisites

None required - Can start fresh.

Uses if available:

  • .shipkit/progress.json - Merge with existing sessions
  • Git - For modified files detection

JSON Schema (Quick Reference)

This skill outputs .shipkit/progress.json using the Shipkit JSON Artifact Convention.

{
  "$schema": "shipkit-artifact",
  "type": "work-memory",
  "version": "1.0",
  "lastUpdated": "2025-01-15T10:00:00Z",
  "source": "shipkit-work-memory",
  "summary": { "totalSessions", "currentPhase", "lastSessionDate", "activeWorkstream", "blockers", "momentum" },
  "sessions": [{ "id", "date", "duration", "workstream", "phase", "accomplished", "filesModified", "decisions", "gotchas", "blockers", "nextSteps", "status" }],
  "workstreams": [{ "id", "name", "status", "startDate", "sessions", "completionEstimate" }],
  "resumePoint": { "lastSession", "immediateNextStep", "context", "openFiles", "relatedArtifacts" },
  "timeline": [{ "date", "event", "type" }]
}

Full schema and field reference: See references/output-schema.md

Realistic example: See references/example.json

Read the full file on GitHub · 420 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 420 lines · 42 tokens per session scan A f4971b6c3321

Subscribe to this mod's changes

shipkit-work-memory is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 2,821 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.