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/ai-debugger-inc/aidb/wrapgit clone --depth 1 https://github.com/ai-debugger-inc/aidbWhat 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
wrap 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.
This is a copy
88% identical to wrap — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
description: Wrap up current work
Wrap up the current work by following the checklist below.
**NOTE: If you are low on context and/or if any of the wrap tasks are easily delegated, feel free to leverage subagents to complete the task(s) to stretch your remaining context.
Checklist:
For all changes/additions made, please:
- Lint the code. It should pass pre-commit checks. If you find linting errors that are not related to your changes, please fix them as well, if possible.
- Verify whether tests need updating. If so, update or add tests to cover your changes. Ensure all tests pass. Always follow existing test patterns.
- When updating or adding new tests, ensure you re using existing fixtures and mocks where applicable. Ensure you adhere to established patterns in the given suite.
- Check to see if there are any related docs. If there are, update them as necessary to account for the changed/added code. Do not add unimportant/minute details to documentation.
- Check if any skills need updates (NOTE: all skill/resource docs should be <=
500 LOC):
- NOT EVERYTHING NEEDS TO BE DOCUMENTED. Only document what is necessary for future maintainers/operators to understand the code and its usage.
- Activate the "skill-developer" skill to assist with skill maintenance.
- Check that proper code reuse was employed, no DRY violations were introduced, and existing codebase patterns were followed. Be wary of magic strings/numbers and use constants/enums where appropriate. Activate the "code-reuse-enforcement" skill to assist with this if needed.
- If there are ANY actionable next steps or current problems/failures, detail them in the form of an actionable summary for the next session.
When finished, provide a commit message (without any single quotes) summarizing the changes made.
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 · 39 lines · 0 tokens per session scan A 149a68e8afdb
wrap is a command published in the GitHub repository ai-debugger-inc/aidb (21 stars, last pushed 3mo ago), licensed Apache-2.0. 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. It is 88% identical to wrap, differing in 22 lines, and is treated as a copy.
Other commands, from other repositories
thunderbot
../../.thunderbot/thunderbot.md.
thunderdown
../../.thunderbot/thunderdown.md.
thunderfix
../../.thunderbot/thunderfix.md.
thunderpush
../../.thunderbot/thunderpush.md.
thundersync
../../.thunderbot/thundersync.md.
create_plan_generic
Create detailed implementation plans with thorough research and iteration.