save-context

save-context is a skill for Claude Code from digital-stoic-org/agent-skills. It costs 48 tokens per session (1,576 once invoked), scanned A, original, MIT.

A skill for saving a compact summary of the current coding session in a `CONTEXT-llm.md` file. The summary preserves work and decisions so a later session can continue.

In plain words
What is it for?
Use it when checkpointing progress, saving a session, or preparing work to resume later. It also preserves exact carried-forward text when required.
Why use it?
It reduces the need to reconstruct the conversation and helps prevent important context from being lost between sessions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; names the AskUserQuestion tool.

Part of the dstoic plugin — 14 skills shipped together

Good fit Use it when checkpointing progress, saving a session, or preparing work to resume later. It also preserves exact carried-forward text when required.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/digital-stoic-org/agent-skills/save-context
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.

Any agent
npx skills add digital-stoic-org/agent-skills --skill save-context
Clone the repo
git clone --depth 1 https://github.com/digital-stoic-org/agent-skills

Made for: Claude Code.

Or install dstoic, the plugin that ships this one along with the rest of its 14 skills.

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/digital-stoic-org/agent-skills/save-context.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/save-context)
Your own site
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/save-context"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/save-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 58
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
  • medium Excessive Agency · line 6
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00048 $0.01576
Opus 5 $0.00024 $0.00788
Sonnet 5 $0.00010 $0.00315
Haiku 4.5 $0.00005 $0.00158

Measured 8d ago against content hash ba56e154a453, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

dstoic/skills/save-context/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Save Context

Save current session state to CONTEXT-{stream}-llm.md with LLM-optimized format.

Target: 2500-3000 tokens MAX | Speed: 3-5 seconds (Not a throwaway summary: the working memory of a multi-session stream, holding accumulating per-role lines.)

⚠️ AskUserQuestion Guard

CRITICAL: After EVERY AskUserQuestion call, check if answers are empty/blank. Known Claude Code bug: outside Plan Mode, AskUserQuestion silently returns empty answers without showing UI.

If answers are empty: DO NOT proceed with assumptions. Instead:

  1. Output: "⚠️ Questions didn't display (known Claude Code bug outside Plan Mode)."
  2. Present the options as a numbered text list and ask user to reply with their choice number.
  3. WAIT for user reply before continuing.

⚠️ VERBATIM RULE

CRITICAL: Never rewrite the text after the colon of a carried-forward line. Never touch a line whose role is not yours — copy it byte-for-byte. A Haiku pass once reworded a user's exact phrasing while explicitly asked to quote it verbatim — hence Sonnet here, not Haiku.

Performance Rules

  1. Use rtk for ALL shell commands
  2. Parallel tool calls — ALL independent calls in one message
  3. Minimize round-trips — gather all data phase 1, reason phase 2, write phase 3

Workflow

Phase 1: Gather Data (parallel)

Bash: rtk ls openspec/changes/ + rtk ls -t CONTEXT-*llm.md
Read: existing CONTEXT-{stream}-llm.md (if present) — needed to carry forward owned lines and to read the `saved:` field for the Phase 3 concurrency check

Stream resolution: First word of $ARGUMENTS = stream name (^[a-zA-Z0-9_-]{1,50}$), rest = description. Empty → reuse prior /load-context stream or AskUserQuestion.

Role resolution: --as <role> flag in $ARGUMENTS > role recorded by the last /load-context for this stream > none (solo session — untagged line format, unchanged behavior).

Phase 1b: Detect Thinking Artifacts (parallel with Phase 1)

If $PRAXIS_DIR is set:

Bash: ls -t "$PRAXIS_DIR/thinking"/*/{project}/ 2>/dev/null | head -10

Where {project} = current project folder name. Collect recent artifact paths written during this session (match conversation timestamps/topics).

Read the full file on GitHub · 100 lines

Files

What ships with it

1 file 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. 8d ago First seen · 100 lines · 48 tokens per session scan A ba56e154a453

Subscribe to this mod's changes

save-context is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 1,576 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens