using-ctx

A persistent memory system for saving and retrieving decisions, facts, patterns, observations, and tasks between coding sessions. It stores notes with categories and project labels.

In plain words
What is it for?
Use it to save durable project knowledge, recall earlier decisions, search stored notes, and check memory status.
Why use it?
It reduces the need to rediscover important project context after the agent's working session ends.

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/zate/cc-plugins/using-ctx
Any agent
npx skills add Zate/cc-plugins --skill using-ctx
Clone the repo
git clone --depth 1 https://github.com/Zate/cc-plugins

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 869 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 $0.00019 $0.00869
Opus 5 $0.00010 $0.00434
Sonnet 5 $0.00004 $0.00174
Haiku 4.5 $0.00002 $0.00087

Measured 2d ago against content hash e077b3521383, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-ctx 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.

plugins/ctx/skills/using-ctx/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ctx: Persistent Memory

You are stateless. Use ctx to persist knowledge across sessions.

For command syntax: ctx --agent-help (index) or ctx --agent-help <command> (detail).

When to Store

Run via Bash BEFORE responding. Store when you learn something that would be useful in a future session.

Core Commands

# Store knowledge
ctx add "content" --type TYPE --tag tier:pinned --tag project:NAME

# Query / recall
ctx recall 'type:decision AND tag:project:NAME'        # immediate results
ctx recall 'tag:tier:reference' --inject               # inject into next prompt

# Search full-text
ctx search "keyword"

# Status
ctx status --agent-out

# Show a node
ctx show <id>

Node types: fact, decision, pattern, observation, hypothesis, task, summary, source, open-question

Tagging Convention

Always include tier: and project: tags on every node.

  • tier:pinned: Critical, loaded every session. Facts, foundational decisions.
  • tier:working: Task-scoped, temporary. Active debugging, current plan state.
  • tier:reference: Durable but not always loaded. Past decisions, resolved issues.
  • tier:off-context: Archived, never loaded.
  • project:NAME: Scope to current project (basename of git root, lowercase).

Recall vs Query

  • ctx recall <query> — run immediately and print results (use this for on-demand lookups)
  • ctx recall <query> --inject — run and queue results for injection at next prompt-submit
  • ctx query <expression> — low-level filtered query (same syntax, no injection support)

--agent-out Flag

Use --agent-out on any result command for dense AOF output optimised for agent consumption (no markdown, no prose):

ctx recall 'tag:project:myapp' --agent-out
ctx status --agent-out
ctx list --agent-out
ctx query 'type:decision' --agent-out

XML Commands (written in responses)

The stop hook parses these from your response text automatically:

<ctx:remember type="decision" tags="project:NAME,tier:reference">
Decision text here.
</ctx:remember>

<ctx:recall query="type:decision AND tag:project:NAME"/>
<ctx:status/>
<ctx:task name="task-name" action="start"/>
<ctx:task name="task-name" action="end"/>
<ctx:summarize nodes="ID1,ID2" archive="true">Summary text.</ctx:summarize>
<ctx:link from="ID1" to="ID2" type="DEPENDS_ON"/>
<ctx:supersede old="OLD_ID" new="NEW_ID"/>

Read the full file on GitHub · 97 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 · 97 lines · 19 tokens per session scan A e077b3521383

Subscribe to this mod's changes

using-ctx is a skill published in the GitHub repository Zate/cc-plugins (10 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 869 once invoked, about $0.0001 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens