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/avansaber/tailtest/tailtest-offgit clone --depth 1 https://github.com/avansaber/tailtestWhat 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 | $0.00057 |
| Opus 5 | $0.00000 | $0.00028 |
| Sonnet 5 | $0.00000 | $0.00011 |
| Haiku 4.5 | $0.00000 | $0.00006 |
Grade A, and why
tailtest-off 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
Pause tailtest for this session.
Set paused: true in .tailtest/session.json. Respond exactly: "tailtest paused. Type /tailtest on to resume."
The PostToolUse hook reads this flag and exits without running tests while paused. No other behaviour changes.
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 · 6 lines · 0 tokens per session scan A bd328954f321
tailtest-off is a command published in the GitHub repository avansaber/tailtest (11 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 57 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 2026-08-31.
Other commands, from other repositories
review-codex
Adversarial security review via OpenAI model — second opinion from a different AI.
sessions
Generate implementation session prompts from a PRD or research doc.
deploy
Command "deploy" from PraveenJayaprakash-JP/repomemory, covering deployment workflow, 1. pre-deploy checks, 2. build verification, 3. environment validation and 4. deployment steps (platform detection).
diagnose
Command "diagnose" from Vimalk0703/shipworthy, covering process, example output, project diagnosis report, critical (fix immediately) and high (fix soon).
plan-review
Deep plan review before implementing any feature, refactor, or significant code change. Enters plan mode - no code changes, just evaluation.
monitor
Monitor repository health, track issues, and identify maintenance tasks.