dump

A session checkpoint tool that saves the important, hard-to-reconstruct parts of current work into the project’s memory files. It prepares those files so a later session can continue.

In plain words
What is it for?
Saving progress when asked to log everything, create a checkpoint, update memory, or dump state, and recording durable claims, decisions, and learnings.
Why use it?
It reduces the risk of losing decisions, discoveries, and unfinished-work context when a coding session ends or runs out of context.

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/emaballarin/ccplugins/dump
Any agent
npx skills add emaballarin/ccplugins --skill dump
Clone the repo
git clone --depth 1 https://github.com/emaballarin/ccplugins

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,338 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 $0.00122 $0.03338
Opus 5 $0.00061 $0.01669
Sonnet 5 $0.00024 $0.00668
Haiku 4.5 $0.00012 $0.00334

Measured yesterday against content hash 78aabb7f536c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

plugins/mindfunnel/skills/dump/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mf:dump — session → project memory

Write the current session's non-derivable state to the project's auto-memory directory so a future session can resume cleanly. Idempotent: can run mid-session, at a natural checkpoint, or at end-of-session.

Important

  1. Never proliferate files. Update existing memory first; create new files only when a topic genuinely deserves its own dossier.
  2. Only log non-derivable signal. Facts recoverable from git log, current code, or AGENTS.md / PROJECT.md do not belong in memory.
  3. SOUL.md and the user-global AGENTS.md are sacred. Propose edits, never apply silently, and only when the insight is genuinely general. The user-global AGENTS.md lives at ~/.mindfunnel/AGENTS.md (reached via ~/.claude/CLAUDE.md); the per-project ./AGENTS.md is a small project-scoped stub owned by the project — don't treat them as the same file.
  4. Convert every "today" / "tomorrow" to an absolute date before writing. Run date -I if uncertain.
  5. Append atomic assertions to the ledger, don't narrate them. Claims, decisions, and learnings that carry a trust level and provenance go to ledger.jsonl (Step 5b); the narrative stays in Markdown. Never double-log one as the other — cross-reference.

Instructions

Step 1: Locate the memory directory

Claude Code's auto-memory system lives at ~/.claude/projects/<slug>/memory/ where <slug> is the project's absolute path with every / replaced by -.

bash -c 'echo ~/.claude/projects/$(echo "$PWD" | sed "s|/|-|g")/memory'

The directory is usually already created by Claude Code. If not, create it before writing.

Step 2: Verify the project is primed

Confirm AGENTS.md and PROJECT.md exist in the project root (these are set up by /mf:prime; under 0.3.0+ they're real committed files, under older versions they may be symlinks — either counts). If either is missing:

  • Flag it and offer to run /mf:prime from the project root.
  • Do not run /mf:prime silently — pre-existing files with the same name matter.
  • Proceed with the dump anyway, noting the priming gap in the final report.

Read the full file on GitHub · 243 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. yesterday First seen · 243 lines · 122 tokens per session scan A 78aabb7f536c

Subscribe to this mod's changes

dump is a skill published in the GitHub repository emaballarin/ccplugins (3 stars, last pushed 26d ago), licensed MIT. It adds 122 tokens to every session and 3,338 once invoked, about $0.0006 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