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/sessiongit 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 | $0.02864 |
| Opus 5 | $0.00000 | $0.01432 |
| Sonnet 5 | $0.00000 | $0.00573 |
| Haiku 4.5 | $0.00000 | $0.00286 |
Grade A, and why
session 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pai session
Session management: list, info, checkpoint, handover, cleanup, slug, tag, route.
Short forms: pai pause, pai end, pai resume <name>.
Synopsis
pai session <subcommand> [options]
Subcommands
| Command | Description |
|---|---|
pai session list |
Resumable sessions catalog — named sessions with resume status. |
pai session restore |
Restore transcripts PAI displaced into sessions/ so claude --resume can find them again. Reports what is unresumable, which checkpoints promise it, and which transcripts are empty. Dry run unless --execute is given. |
pai session info <project-slug> <number> |
Show full details for a specific session |
pai session rename <project-slug> <number> <new-slug> |
Rename a session note — updates file on disk, H1 title, and registry |
pai session slug <project-slug> <number> |
Generate a descriptive slug from the session JSONL transcript |
pai session tag <project-slug> <number> [tags...] |
Set or show tags on a session. Tags can be space-separated or comma-separated. |
pai session route <project-slug> <number> <target-project> |
Create a cross-reference link from a session to a target project |
pai session handover [project-slug] [number-or-latest] |
Write a ## Continue section to the project's TODO.md. |
pai session checkpoint <message> |
Append a timestamped checkpoint to the active session note. |
pai session autosave |
Refresh the ## Continue checkpoint from the transcript and working tree. |
pai session active |
Show currently active Claude Code sessions. |
pai session recent |
[Deprecated] Use pai session list or pai sessions instead. |
pai session goto <name-or-id> |
Go to a session: resume if a resumable snapshot exists, start fresh otherwise. |
pai session pause |
Write a ## Continue checkpoint to the project's TODO.md. |
pai session auto-route |
Auto-detect which project this session belongs to. |
pai session cleanup [project-slug] |
Clean up session notes: delete empties, auto-name unnamed, move into YYYY/MM/ hierarchy, renumber |
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 · 313 lines · 0 tokens per session scan A e42c7d65d9e0
session 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 2,864 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.