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/prunegit 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 | $0.00695 |
| Opus 5 | $0.00000 | $0.00347 |
| Sonnet 5 | $0.00000 | $0.00139 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
prune 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mindlink prune
Review and retire stale MEMORY.md entries interactively.
Synopsis
mindlink prune [--dry-run] [--all]
Description
MEMORY.md entries accumulate over time. A decision made six months ago that was later reversed, a "current focus" entry that describes work completed three months ago — these entries linger and degrade the quality of your AI's context.
mindlink prune surfaces entries by age and lets you decide what to do with each one. Entries can be kept, moved to an ## Archive section, or permanently deleted.
MindLink never auto-deletes content. Archived entries are moved to ## Archive at the bottom of MEMORY.md — they are always kept for reference unless you explicitly delete them.
Entries are identified by <!-- added: YYYY-MM-DD --> timestamps, which your AI appends to every new entry it writes.
Staleness Thresholds
| Section | Warn after |
|---|---|
## Current Focus |
14 days |
## Decisions |
180 days |
## Conventions |
180 days |
## Architecture |
365 days |
## User Profile |
Never |
## Important Context |
Never |
Entries without a timestamp are not flagged (no reference date to compare against).
Interactive Flow
◉ MindLink Prune
/Users/you/my-project/.brain/MEMORY.md
Scanning MEMORY.md for stale entries...
Found 2 entries to review.
───────────────────────────────────────────────────────
Section: Current Focus
Entry:
Building billing integration in src/api/billing.ts
Added: 2026-01-15 (87 days ago) — threshold: 14 days
❯ Keep (leave as-is)
Archive (move to ## Archive section)
Delete (remove permanently)
Skip remaining
───────────────────────────────────────────────────────
✓ 1 entry archived
· 1 entry kept
✓ MEMORY.md updated.
Options
| Flag | Description |
|---|---|
--dry-run |
Show what would be flagged without making any changes |
--all |
Show all timestamped entries regardless of age |
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 · 118 lines · 0 tokens per session scan A a597c4bfb779
prune 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 695 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.
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.