save-context

save-context is a skill for Claude Code, Codex from pioneerjeff-labs/packwright. It costs 0 tokens per session (488 once invoked), scanned A, original, MIT.

A session handoff tool that records the current objective, decisions, changed files, checks performed, and unanswered questions in project memory files.

In plain words
What is it for?
Use it when closing a session, handing work to someone else, or preserving the current state of a project for later.
Why use it?
It prevents important project context from being lost between sessions or at milestone handoffs.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

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/pioneerjeff-labs/packwright/save-context
Any agent
npx skills add pioneerjeff-labs/packwright --skill save-context
Clone the repo
git clone --depth 1 https://github.com/pioneerjeff-labs/packwright

Made for: Claude Code, Codex.

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 save-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/pioneerjeff-labs/packwright/save-context.svg)](https://agentmods.dev/skills/pioneerjeff-labs/packwright/save-context)
Your own site
<a href="https://agentmods.dev/skills/pioneerjeff-labs/packwright/save-context"><img src="https://agentmods.dev/badge/skills/pioneerjeff-labs/packwright/save-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 488 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 5.1 $0.00000 $0.00488
Opus 5 $0.00000 $0.00244
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 5d ago against content hash 3a02a37e562f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

save-context 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 5d 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.

examples/atlas-work/skills/save-context/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Save Context

Use this skill at milestone handoff, session close, or when the user asks Atlas to preserve state.

Procedure

  1. Identify the current objective, scope, decisions, changed files, verification, and open questions.
  2. Update the canonical owner file instead of copying the same fact across layers.
  3. Update memory/projects/<slug>.md for project state, decisions, open loops, and project-specific sources.
  4. Update memory/session-index.md for session/thread lookup entries, not project state summaries.
  5. Update memory/source-map.md for source-of-truth paths, verification routes, and lookup pointers.
  6. Update memory/todos.md for action queues and commitments.
  7. Update memory/collaboration.md only for stable collaboration calibrations.
  8. Update memory/index.md only when active projects, memory owners, or routing rules change.
  9. Report what was saved and what remains unsaved.

Memory Tracks

  • index: Default memory router; points to active projects and canonical memory owners.
  • profile: Stable user, subject, learner, creator, or relationship facts that matter across workstreams.
  • workstreams: Domain router for long-running work areas; route to workstream detail files when useful.
  • workstream_details: Optional detailed domain files for mature workstreams and future agent promotion.
  • projects: Source of truth for project state, decisions, open loops, and project-specific sources.
  • session_index: Lookup index for prior sessions, thread recall, and earlier work references.
  • source_map: Source registry for lookup and verification paths; not a knowledge base.
  • todos: Action queues and commitments.
  • collaboration: Learned collaboration calibrations and repair notes.
  • pinned: Compatibility-only in the MVP; avoid using it as a normal memory layer.
  • light: Compatibility alias for memory/session-index.md.
  • heavy: Persist context into the canonical owner files.
  • relationship: Compatibility alias for memory/collaboration.md.
  • workspace: Domain-first draft, artifact, and archive storage; important outputs are indexed in memory/source-map.md.

Read the full file on GitHub · 40 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. 5d ago First seen · 40 lines · 0 tokens per session scan A 3a02a37e562f

Subscribe to this mod's changes

save-context is a skill published in the GitHub repository pioneerjeff-labs/packwright (5 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 488 tokens. 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

openlore

Query and publish to an OpenLore knowledge base over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings.

aakarim/OpenLore · 42 tokens

openlore-housekeeping

Audit and maintain a shared OpenLore knowledge base. Use on a schedule or on request to find stale docs, broken links, unreviewed inbox items, and missing skill coverage, then publish an audit report.

aakarim/OpenLore · 48 tokens

cortadel

Cortadel is a self-hosted, bi-temporal graph memory server for AI agents — one .NET container exposing a REST API and an MCP endpoint over FalkorDB or Memgraph, with intent-aware writes (store/invalidate/delete-entity/touch/resolve), LLM-verified dedup with a negation guard, and hybrid BM25+vector+RRF retrieval…

cortadel/cortadel · 178 tokens

forget

Retract or permanently erase a Cortadel memory. Use when the user says "forget that...", "X is no longer true", "that's outdated", "delete this memory", or "permanently remove ". Default path is a natural-language retraction that keeps history queryable; hard, unrecoverable deletion only happens on an explicit…

cortadel/cortadel · 77 tokens

history

Reconstruct what Cortadel memory said as of a past date, or trace a fact's supersession chain (what replaced or invalidated it, and when). Use when the user asks what they believed on a given date, wants to see superseded/historical versions of a fact, or asks how something changed over time. mem0 has no equivalent …

cortadel/cortadel · 81 tokens

recall

Search Cortadel memory deliberately — broader, filtered, or budgeted retrieval beyond what the automatic per-prompt recall gives. Use when the user asks to look something up in memory, search past context, or wants results scoped by project/tag/type — e.g. "search my memories for X", "what do we know about Y", "recall…

cortadel/cortadel · 77 tokens