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/syncgit 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 | $0.00553 |
| Opus 5 | $0.00000 | $0.00277 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
sync 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mindlink sync
Watch for shared context written by other sessions and surface it automatically.
Run this in a dedicated background terminal tab while your AI sessions are active. It stays running until you stop it (Ctrl+C).
Synopsis
mindlink sync [--once] [--no-progress]
What "watch mode" means
Watch mode is the default — when you run mindlink sync with no flags, the process stays alive. It watches .brain/SHARED.md for any new content written by other sessions in this project. The moment another session appends a discovery or decision, sync detects the change and prints a notification so you know to tell your AI to check SHARED.md.
This is designed to run in a separate terminal tab alongside your AI session, not as a one-shot command.
--once runs a single check and exits — useful when you just want to see what's been shared so far without keeping a watcher running.
If you enabled auto-sync during mindlink init, sync runs automatically in the background — you don't need to run this manually.
Options
| Flag | Description |
|---|---|
--once |
Sync once and exit instead of watching continuously |
--no-progress |
Suppress progress output (useful in scripts) |
Examples
Watch mode (default) — runs until you stop it:
mindlink sync
Sync once and exit:
mindlink sync --once
Output
Watch mode:
Watching for changes... (Ctrl+C to stop)
[Apr 9 14:32] Session A wrote 3 new entries → synced ✓
[Apr 9 14:45] Session B wrote 1 new entry → synced ✓
Single run:
Syncing shared context...
Session A → 3 new entries
Session B → 1 new entry
[████████████████████] 100%
✓ SHARED.md merged. Both sessions are now in sync.
Nothing to sync:
✓ Already in sync. No new entries to merge.
Changing Auto-Sync Setting
To enable or disable auto-sync (set during mindlink init):
mindlink config
Select Auto-sync from the menu.
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 · 97 lines · 0 tokens per session scan A d90b597d6214
sync 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 553 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.