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/mnott/pai/registrygit clone --depth 1 https://github.com/mnott/PAIWhat 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 | $0.00955 |
| Opus 5 | $0.00000 | $0.00477 |
| Sonnet 5 | $0.00000 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
registry 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pai registry
Registry maintenance: scan, migrate, stats, rebuild
Synopsis
pai registry <subcommand> [options]
Subcommands
| Command | Description |
|---|---|
pai registry scan |
Walk ~/.claude/projects/ and configured scan_dirs, upsert all projects |
pai registry migrate |
Import data from ~/.claude/session-registry.json |
pai registry stats |
Show summary statistics for the registry |
pai registry rebuild |
Erase all registry data and rebuild from the filesystem (destructive) |
pai registry dedupe |
Merge registry rows that describe the same project. |
pai registry reconnect |
Point projects back at the transcripts they lost. |
pai registry lookup |
Find the project slug for a filesystem path (for use in scripts) |
pai registry scan
Walk ~/.claude/projects/ and configured scan_dirs, upsert all projects
Options
| Option | Description | Default |
|---|---|---|
--add-dir <path> |
Add a directory to scan_dirs config | |
--remove-dir <path> |
Remove a directory from scan_dirs config | |
--show-dirs |
Show currently configured scan directories | |
--quick |
Minimal output mode (used by hooks and daemon) |
pai registry migrate
Import data from ~/.claude/session-registry.json
pai registry stats
Show summary statistics for the registry
pai registry rebuild
Erase all registry data and rebuild from the filesystem (destructive)
pai registry dedupe
Merge registry rows that describe the same project.
Two spellings of one directory (e.g. via a symlinked path prefix) register as separate projects and split session history between them. Rows are grouped by resolved path, so a merge only happens when the paths are provably identical. Dry-run by default; --execute backs up the registry first and merges in one transaction.
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 · 104 lines · 0 tokens per session scan A 389f87e1d511
registry is a command published in the GitHub repository mnott/PAI (45 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 955 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.