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 agentmods add commands/404-not-found/mindlink/exportgit clone --depth 1 https://github.com/404-not-found/mindlinkWhat 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 | $0.00000 | $0.00575 |
| Opus 5 | $0.00000 | $0.00287 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
export 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mindlink export
Export your project's AI memory to a shareable zip file.
Run in your terminal. The zip can be shared with teammates, used as a backup, or imported into another machine.
Synopsis
mindlink export [--output <path>] [--include-agents]
Description
Packages your .brain/ folder into a zip file named {project}-brain-{date}.zip. You can share this zip with anyone — they import it with mindlink import and their AI agent wakes up knowing everything your project knows.
If you run this interactively (no --output flag), MindLink asks where to save the file.
Use Cases
Onboard a new teammate
mindlink export --output ~/Desktop
# Send them: my-app-brain-2026-04-10.zip
# They run: mindlink import my-app-brain-2026-04-10.zip
Back up before a reset
mindlink export --output ~/backups
mindlink reset
Share context with a consultant
mindlink export --include-agents --output ~/Desktop
# They get the memory AND the agent instruction files
What Gets Exported
| File | Included |
|---|---|
.brain/MEMORY.md |
✓ always |
.brain/SESSION.md |
✓ always |
.brain/SHARED.md |
✓ always |
.brain/LOG.md |
✓ always |
.brain/LOG-*.md (archives) |
✓ always |
CLAUDE.md, CURSOR.md, etc. |
Only with --include-agents |
.brain/config.json |
✗ never (machine-specific) |
Options
| Flag | Description |
|---|---|
--output <path> |
Directory or full .zip path to save the file |
--include-agents |
Also include agent instruction files |
Output
✓ .brain/MEMORY.md
✓ .brain/SESSION.md
✓ .brain/SHARED.md
✓ .brain/LOG.md
✓ Exported to: /Users/yuanhong/Desktop/my-app-brain-2026-04-10.zip
To import on another machine or project:
mindlink import my-app-brain-2026-04-10.zip
Related Commands
mindlink import— import a zip into the current projectmindlink reset— wipe memory (export first if you want a backup)
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.
- 2d ago First seen · 91 lines · 0 tokens per session scan A eaf1e8df6223
export is a command published in the GitHub repository 404-not-found/mindlink (11 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 575 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.