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/skillgit 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 | $0.00543 |
| Opus 5 | $0.00000 | $0.00271 |
| Sonnet 5 | $0.00000 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
skill 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pai skill
Skill telemetry and (future) discovery for the self-educating skill system
Synopsis
pai skill <subcommand> [options]
Subcommands
| Command | Description |
|---|---|
pai skill telemetry |
Show skill-invocation telemetry (triggers, last used, projects) |
pai skill telemetry
Show skill-invocation telemetry (triggers, last used, projects)
Options
| Option | Description | Default |
|---|---|---|
--scope <scope> |
Governance scope | default |
--status <status> |
Filter by status: trial | active | archived | |
--limit <n> |
Maximum rows | 50 |
--json |
Output raw JSON |
Examples
# Which skills have actually been triggered, most-used first
pai skill telemetry
# Only skills still in trial (quarantined, not yet promoted)
pai skill telemetry --status trial
# Machine-readable output for dashboards
pai skill telemetry --json
See Notes/swarm/skills-self-educating.md for the full self-educating loop
(discovery, sandbox trial, telemetry, adaptation).
See also
pai backup · pai clear-names · pai daemon · pai db · pai end · pai help · pai identity · pai kg · pai mcp · pai memory · pai notify · pai observation · pai obsidian · pai pause · pai project · pai projects · pai registry · pai restore · pai session · pai sessions · pai setup · pai shell-init · pai task · pai topic · pai update · pai zettel
Run pai help <area> to read any of these in the terminal.
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 · 55 lines · 0 tokens per session scan A 2eae27ab9fb3
skill 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 543 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.