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 agents/liza-mas/liza/worktree-path-constructiongit clone --depth 1 https://github.com/liza-mas/lizaWrote 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/agents/liza-mas/liza/worktree-path-construction)<a href="https://agentmods.dev/agents/liza-mas/liza/worktree-path-construction"><img src="https://agentmods.dev/badge/agents/liza-mas/liza/worktree-path-construction.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 | $0.00000 | $0.00403 |
| Opus 5 | $0.00000 | $0.00201 |
| Sonnet 5 | $0.00000 | $0.00081 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
worktree-path-construction 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 5d 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
The worktree root already ends in the task id: .worktrees/<task-id>. Relative paths inside the worktree are rooted there — you do NOT prepend the task id again.
Anti-pattern observed (burned 72 turns before self-diagnosing):
/path/to/project/.worktrees/my-task-id/my-task-id/specs/plans/...
^^^^^^^^^ ^^^^^^^^^
worktree (duplicate, always wrong)
This happens when the agent holds two fragments in memory — the absolute worktree root AND a task-named relative path — and concatenates them without noticing the overlap. Every access returns ENOENT for a file that exists one level up, and the agent often fails to recognize the pattern.
Rules:
- Every path variable (
{{.WorktreePath}},{{.Worktree}}) already points at.worktrees/<task-id>. Join only with the path below that root. - If you catch yourself typing
.worktrees/<id>/<id>/, strip one segment. - If you see repeated ENOENT on paths that "should exist," immediately run
lson the parent dir to confirm the layout before constructing more paths.
Runtime guard:
A PreToolUse hook (worktree-path-guard.sh) denies Read/Write/Edit calls whose file_path matches .worktrees/<id>/<id>/. The deny reason names the duplicate segment so the fix is obvious.
Related lesson: worktree-file-path-consistency.md covers a different quirk — Claude Code's Edit tool tracking reads by exact string match. Same overall prescription (use the path variable, don't reconstruct), different root cause.
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.
- 5d ago First seen · 28 lines · 0 tokens per session scan A aec4b04bb2b9
worktree-path-construction is an agent published in the GitHub repository liza-mas/liza (364 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 403 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.