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.
npx skills add artem-from-ua/claude-plugins --skill ctx-dumpgit clone --depth 1 https://github.com/artem-from-ua/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/artem-from-ua/claude-plugins/ctx-dump)<a href="https://agentmods.dev/skills/artem-from-ua/claude-plugins/ctx-dump"><img src="https://agentmods.dev/badge/skills/artem-from-ua/claude-plugins/ctx-dump.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.00765 |
| Opus 5 | $0.00039 | $0.00382 |
| Sonnet 5 | $0.00015 | $0.00153 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
ctx-dump 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ctx-dump — Dump In-Memory Session Context
Dump the verbatim content from Claude's context window to a file.
Unlike /ctx-show (which re-reads disk), this outputs what Claude actually sees.
Flags
| Flag | Description |
|---|---|
--file |
(default) Write to /tmp/claude-context-dump-{timestamp}.md and print the path |
--stdout |
Print full content to terminal instead of writing to file |
Sources to Dump (in load order)
Scan your context window and extract ALL of the following. Each appears inside
<system-reminder> tags or as claudeMd blocks injected at session start.
~/.claude/CLAUDE.md— global user instructions (labeled "user's private global instructions for all projects"){project}/CLAUDE.md— project instructions (labeled "project instructions, checked into the codebase")~/.claude/projects/{hash}/memory/MEMORY.md— auto-memory (labeled "user's auto-memory, persists across conversations")- All SessionStart hook outputs — any other content blocks in
system-remindertags (plugin-injected rules, playbook presets, git-branch-naming rules, etc.) - Available skills list — the skill names and descriptions loaded at session start
- gitStatus — the git status snapshot from conversation start
- currentDate — the date injected at session start
Output Format
# Session Context Dump (from memory)
Generated: {YYYY-MM-DD HH:MM}
---
## Source: ~/.claude/CLAUDE.md (global user instructions)
{verbatim content}
---
## Source: {project}/CLAUDE.md (project instructions)
{verbatim content}
---
## Source: Auto-memory (MEMORY.md)
{verbatim content}
---
## Source: SessionStart hook — {identifier}
{verbatim content for each hook output, repeat section as needed}
---
## Source: Available skills
{skill listing as it appears in context}
---
## Source: gitStatus
{verbatim git status block}
---
## Source: currentDate
{verbatim date value}
Steps
- Parse the flag argument. Default is
--file. - Scan your current context window for all sources listed above.
- For EACH source: copy the content verbatim — no translation, no abbreviation, no omission of "large blocks", no reformatting. Preserve original markdown, code blocks, and whitespace exactly as they appear.
- Assemble the output following the format above.
--filemode: Use the Write tool to save to/tmp/claude-context-dump-{timestamp}.md(timestamp:YYYYMMDD-HHMMSS). Report the file path.--stdoutmode: Output the full assembled content directly in the response.
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.
- 8d ago First seen · 101 lines · 77 tokens per session scan A ad9d65268b60
ctx-dump is a skill published in the GitHub repository artem-from-ua/claude-plugins (11 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 765 once invoked, about $0.0004 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.
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.
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.…
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…
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.
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…
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.