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/frayo44/agent-view/avgit clone --depth 1 https://github.com/Frayo44/agent-viewWhat 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 | $0.00410 |
| Opus 5 | $0.00000 | $0.00205 |
| Sonnet 5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
av 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.
What it actually says
Use the av CLI to manage agent-view sessions without the TUI.
Create a session
av --new --path $PROJECT_PATH --tool claude
Flags:
--path <dir>— Project directory (default: cwd)--tool <name>— claude | custom (default: claude)--title <name>— Session title (default: auto-generated)--command <cmd>— Custom command (requires--tool custom)--group <path>— Group path (default: my-sessions)--worktree— Create in a git worktree--branch <name>— Worktree branch name (requires--worktree)--base-develop— Base worktree on develop branch--resume— Resume existing Claude session--skip-permissions— Skip Claude permission prompts
List sessions
av --list
av --list --status running
av --list --json
Session actions
av --stop <id-or-title>
av --restart <id-or-title>
av --attach <id-or-title>
av --delete <id-or-title> --force
av --delete <id-or-title> --worktree --force
Send instructions to a running session
av --send <id-or-title> Fix the snackbar so it appears above the bottom nav bar
Sends the message as input to the session's tmux pane (types it and presses Enter). Use this to give tasks to running Claude/agent sessions programmatically.
Session info
av --status <id-or-title>
av --info <id-or-title>
av --info <id-or-title> --json
Sessions can be referenced by full ID, title, or ID prefix. Changes made via CLI appear in any running TUI instance automatically.
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 · 56 lines · 0 tokens per session scan A 936514638d09
av is a command published in the GitHub repository Frayo44/agent-view (368 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 410 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.