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.
git clone --depth 1 https://github.com/axiomantic/spellbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/axiomantic/spellbook/merge-worktree-verify)<a href="https://agentmods.dev/commands/axiomantic/spellbook/merge-worktree-verify"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/merge-worktree-verify.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00024 | $0.00825 |
| Opus 5 | $0.00012 | $0.00413 |
| Sonnet 5 | $0.00005 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade C, and why
merge-worktree-verify scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
reach for `--force` or `rm -rf` to make the error go away. How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invariant Principles
- Full suite, no shortcuts — Run the complete test suite; no subsets.
- Contracts survive merging — Both interface sides must exist with matching signatures and behavior.
- Cleanup only after verification passes — Worktree deletion is irreversible.
Phase 4: Final Verification
Run in order. All must pass before Phase 5.
- Full test suite — All tests must pass.
- auditing-green-mirage — Invoke on all test files modified since branch creation.
- Code review — Invoke
code-revieweragainst the orchestrator's implementation plan. - Interface contract check — For each contract:
- Both sides of interface exist
- Type signatures match
- Behavior matches specification
Phase 5: Cleanup
Remove each worktree with the non-destructive form first:
git worktree remove [worktree-path]
On failure, list what is at risk and ask via AskUserQuestion, never as prose:
git -C [worktree-path] status --porcelain -uall
- question:
Running: git worktree remove [worktree-path] --force/Effect: discards the uncommitted changes listed above/Recoverable: no - options:
Run it(uncommitted work in that worktree is destroyed) andCancel(worktree kept intact).
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.
- 4d ago First seen · 104 lines · 24 tokens per session scan C 18a716343840
merge-worktree-verify is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 825 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
test-coverage
Analyze test coverage and generate missing tests to reach 80%+ coverage.
watch-ci
Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.
pr-ready
Run the project's pre-commit review loop to determine whether the current branch is ready to push — lint, tests, parallel pr-review-toolkit agents plus an over-engineering audit, fix-and-re-run until convergence.