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 skills add try-works/recursive-mode --skill recursive-worktreegit clone --depth 1 https://github.com/try-works/recursive-modeWrote 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/try-works/recursive-mode/recursive-worktree)<a href="https://agentmods.dev/skills/try-works/recursive-mode/recursive-worktree"><img src="https://agentmods.dev/badge/skills/try-works/recursive-mode/recursive-worktree/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/try-works/recursive-mode/recursive-worktree"><img src="https://agentmods.dev/badge/skills/try-works/recursive-mode/recursive-worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00041 | $0.01048 |
| Opus 5.5 | $0.00016 | $0.00419 |
| Sonnet 5.5 | $0.00008 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
recursive-worktree 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 1mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
recursive-worktree
Purpose
Use this skill at the start of a recursive-mode run to set up an isolated worktree before Phase 1+ work begins.
The canonical overall workflow still lives in /.recursive/RECURSIVE.md. This skill covers only the worktree-isolation discipline for 00-worktree.md.
Hard Rule
Do not proceed with recursive-mode phase work until:
- A feature-branch worktree exists.
- The worktree directory is git-ignored if it lives inside the repo.
- Project setup has completed.
- A clean or explicitly acknowledged baseline test state has been recorded.
Default Location Order
Use this priority:
- Existing
.worktrees/ - Existing
worktrees/ - A preference documented in repo instructions
- Ask the user
- Default to
.worktrees/
Global fallback location:
~/.config/recursive-mode/worktrees/<project-name>/
Main Branch Protection
If the current branch is main or master, default to creating a worktree on a feature branch:
git worktree add .worktrees/<run-id> -b recursive/<run-id>
cd .worktrees/<run-id>
If the user explicitly insists on main-branch work, record that exception in 00-worktree.md.
Minimum Phase 0 Checklist
00-worktree.md must cover:
- selected worktree location
- git-ignore verification
- branch name and worktree path
- setup commands executed
- baseline test command and result
- normalized diff basis fields including
Baseline type,Baseline reference,Comparison reference,Normalized baseline,Normalized comparison, andNormalized diff command - explicit note that subsequent phases run from the worktree
- the required
## TODOheading from the scaffold
Suggested Commands
Check branch:
git branch --show-current
Check ignore status:
git check-ignore -q .worktrees || git check-ignore -q worktrees
Create worktree:
git worktree add .worktrees/<run-id> -b recursive/<run-id>
Setup Guidance
Run the setup command that matches the repo:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 139 lines · 41 tokens per session scan A 53810c60b121
recursive-worktree is a skill published in the GitHub repository try-works/recursive-mode (136 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,048 once invoked, about $0.0002 per session on Opus 5.5. 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
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
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.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.