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/young1the/pets-driven/bringgit clone --depth 1 https://github.com/young1the/pets-drivenWhat 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 | $0.00034 | $0.00761 |
| Opus 5 | $0.00017 | $0.00380 |
| Sonnet 5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
bring 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 yesterday.
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
Populate an agent's working folder with the project it should work on. The folder may be empty (freshly created for the agent) and you bring the project repository into it, then hand it off to a pet. Do the steps in order, one prompt at a time, and stop if the user cancels.
-
Confirm the target folder. Default to the current working directory. Show it and ask whether to use it or a different path. This is where the project lands and becomes the pet's home folder. For a
git worktree, the folder must be empty or not yet exist; for agit clone, it must be empty or non-existent. If the folder already holds a repository, say so and stop — there is nothing to bring in. -
Ask for the source. Find out where the project comes from. Two shapes:
- A remote URL (e.g.
https://github.com/org/repo.git,git@…) → clone. - A local repository path (a folder that is already a git repo) → add a worktree from it.
If the source is ambiguous, ask. You can detect a local repo with
git -C "<path>" rev-parse --is-inside-work-tree. - A remote URL (e.g.
-
Bring in the repository.
Remote URL → clone. Clone directly into the target folder:
git clone "<url>" "<target-folder>"If the user wants a specific branch, add
--branch "<branch>".Local repo → worktree. A worktree gives the agent an isolated checkout on its own branch, leaving the source repo untouched. Ask for the branch:
- New branch (default for isolated agent work) off the source's current HEAD or a base the user names.
- Existing branch to check out as-is.
Create it from the source repo (works even when the target folder already exists but is empty):
# new branch git -C "<local-repo>" worktree add "<target-folder>" -b "<branch>" # existing branch git -C "<local-repo>" worktree add "<target-folder>" "<branch>"If
git worktree addfails with a permission/sandbox error, tell the user and stop rather than retrying blindly. -
Verify. Confirm the repo is in place and report the branch:
git -C "<target-folder>" branch --show-current git -C "<target-folder>" worktree list # for the worktree caseDo not run dependency installs or builds unless the user asks — keep this step to bringing in the code.
-
Hand off to a pet. The folder is now ready for a pets-driven pet. If no pet is bound to this folder yet, tell the user they can hatch one with
/pets-driven:hatch. Once a pet is bound and the desktop app is running, it reacts to the agent's work automatically — nothing to run here. -
Report the result: the target folder, whether it was a clone or a worktree, the checked-out branch, and whether a pet is bound here.
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.
- yesterday First seen · 72 lines · 34 tokens per session scan A 84874780cdee
bring is a command published in the GitHub repository young1the/pets-driven (1 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 761 once invoked, about $0.0002 per session on Opus 5. 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
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.