Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/robertbarclayy/conductynpx agentmods add skills/robertbarclayy/conducty/conducty-worktreesWrote 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/skills/robertbarclayy/conducty/conducty-worktrees)<a href="https://agentmods.dev/skills/robertbarclayy/conducty/conducty-worktrees"><img src="https://agentmods.dev/badge/skills/robertbarclayy/conducty/conducty-worktrees.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00870 |
| Opus 5 | $0.00032 | $0.00435 |
| Sonnet 5 | $0.00013 | $0.00174 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
conducty-worktrees 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conducty Worktrees — Parallel Isolation
Use git worktrees (Bash) to isolate parallel prompts that target the same repository, preventing conflicts during concurrent execution.
When to Use
Use worktrees when a parallelization group has two or more prompts targeting the same repository. If all prompts in a group target different repos, worktrees are unnecessary.
[!tip] Claude Code shortcut When dispatching a subagent via the Task tool, pass
isolation: "worktree"to let the harness create and clean up a temporary worktree automatically. Use this skill when you need explicit, named worktrees that survive across multiple subagent dispatches in the same group.
Tracer Worktree Strategy
The tracer prompt (marked ★ TRACER) runs on the main branch, not in a worktree. It validates plan assumptions against the real repo state. Only after the tracer passes do you create worktrees for the remaining prompts.
This ensures the tracer tests reality, not an isolated copy.
Workflow
Step 1: Wait for Tracer
The tracer prompt executes first on the main branch (via [[conducty-execute]]). If it passes, proceed. If it fails, the plan needs revision — don't create worktrees for a flawed plan.
Step 2: Create Worktrees
For each remaining prompt that targets the same repo:
cd /path/to/project
git worktree add ../conducty-wt-P{N} -b conducty/P{N}
This creates:
- A sibling directory
conducty-wt-P{N}with a full working copy - A branch
conducty/P{N}tracking the current HEAD (which now includes the tracer's commits)
Update each prompt's Directory field in the plan to point to the worktree path (Edit tool).
Step 3: Verify Baselines
For each worktree, run the project's test suite or build command (Bash):
cd ../conducty-wt-P{N}
# run project-specific test/build command
If the baseline fails, the worktree inherits a broken state — flag this before execution begins. A broken baseline wastes the entire prompt.
Step 4: Execute
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.
- 8d ago First seen · 100 lines · 64 tokens per session scan A 02d2f06ff251
conducty-worktrees is a skill published in the GitHub repository robertbarclayy/conducty (176 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 870 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".