agents-remember: Skill for Claude Code

.agents/skills/c-09-git-worktree-manager/SKILL.md

c-09-git-worktree-manager is a skill for Claude Code, Codex from Foxfire1st/agents-remember. It costs 42 tokens per session (8,760 once invoked), scanned A, original, MIT.

A skill for managing coding tasks that use Git worktrees, which are separate working directories linked to the same Git repository. It covers starting, integrating, reporting, finalising, and cleaning up these tasks.

In plain words
What is it for?
Use it to run worktree-backed tasks, preview and apply worktree operations, integrate completed changes, finalise task state, and remove temporary worktrees safely.
Why use it?
It keeps delegated work isolated and makes approval, memory compatibility, integration, and cleanup steps explicit.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Foxfire1st/agents-remember's own configuration. It tells Claude Code and Codex how to work on agents-remember itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents-remember configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Foxfire1st/agents-remember. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Foxfire1st/agents-remember/main/.agents/skills/c-09-git-worktree-manager/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Foxfire1st/agents-remember

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for c-09-git-worktree-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-09-git-worktree-manager/github.svg)](https://agentmods.dev/skills/foxfire1st/agents-remember/c-09-git-worktree-manager)
Your own site
<a href="https://agentmods.dev/skills/foxfire1st/agents-remember/c-09-git-worktree-manager"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-09-git-worktree-manager/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.

agentmods 80×15 button for c-09-git-worktree-manager

Your own site · 80×15
<a href="https://agentmods.dev/skills/foxfire1st/agents-remember/c-09-git-worktree-manager"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-09-git-worktree-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.08760
Opus 5.5 $0.00017 $0.03504
Sonnet 5.5 $0.00008 $0.01752
Haiku 4.5 $0.00004 $0.00876

Measured 1mo ago against content hash afa1d5a58f56, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

c-09-git-worktree-manager 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.

.agents/skills/c-09-git-worktree-manager/SKILL.md · 564 lines

How it starts

The opening of the file, as written. The whole thing — 564 lines — stays where its author put it; the contents beside it link to each section on GitHub.

c-09-git-worktree-manager Git Worktree Manager

Use this skill when a task should run through an explicit code/memory worktree wrapper.

The c-09-git-worktree-manager skill wraps the existing light-task or external workflow (a build that fits one session still rides a THIN w-02-light-task-workflow doc — chat is never a build route, per the l-01-agent-lifecycles invariant). It owns Git worktree state, series contracts, leaf enclosures, external-memory compatibility checks, integration, lifecycle finalization, and cleanup. It does not replace the workflow that performs the actual implementation.

For closeout, use the c-12-closeout skill. The c-09-git-worktree-manager skill only supplies the worktree-specific contract path and integration/finalization follow-up rules.

MCP Tools

Use the Agents Remember MCP worktree tools as the normal installed runtime entry point:

Preview first. worktree_start, worktree_integrate, worktree_cleanup, and lifecycle_finalize_task now apply by default. Run each once with dry_run=true to inspect the plan, confirm, then run the real apply (omit dry_run).

worktree_start(repo_id="<repo-id>", task_name="<task>", worktree_name="<leaf-worktree>", leaf_id="<leaf-id>", workflow_kind="light-task")
worktree_enclosure_adopt(contract_path="<stable series-contract.md>", expected_worktree_group="<exact root>", rationale="<audit reason>", dry_run=true)
worktree_attach(repo_id="<repo-id>", task_name="<task>", leaf_id="<leaf-id>")
worktree_status(repo_id="<repo-id>", task_name="<task>", leaf_id="<leaf-id>")
worktree_sync(contract_path="<enclosure series-contract.md>")
closeout_door(request={action:"declare|status|defer|resume|withdraw|update-provenance", contract_path:"<enclosure series-contract.md>", ...})
closeout_queue(request={action:"status|rebuild", sprint_task_document_ref:{repository:"<repo-id>", path:"<sprint task.json>"}})
worktree_closeout_preview(contract_path="<enclosure series-contract.md>", code_commit_message="<message>", memory_commit_message="<message>")
worktree_closeout_apply(contract_path="<enclosure series-contract.md>", intent_note="<developer intent>", code_commit_message="<message>", memory_commit_message="<message>")
worktree_operation_control(contract_path="<enclosure series-contract.md>", operation_kind="closeout", action="cancel|resume", expected_generation=<generation>, intent_note="<audit intent>")
worktree_operation_control(contract_path="<enclosure series-contract.md>", operation_kind="integrate|direct-landing", action="retry|recover|cancel|retire|supersede", expected_generation=<generation>, intent_note="<audit intent>")
worktree_legacy_operation(contract_path="<enclosure series-contract.md>", operation_kind="closeout|integrate|direct-landing", action="inspect|migrate|archive", ...)
worktree_integrate(contract_path="<enclosure series-contract.md>", strategy="ff-only")
worktree_cleanup(contract_path="<enclosure series-contract.md>", teardown_providers=true)
worktree_abandon(contract_path="<enclosure series-contract.md>", force=false)
task_reopen(contract_path="<enclosure series-contract.md>", dry_run=true)
lifecycle_finalize_task(contract_path="<enclosure series-contract.md>", task_doc_path="<task.json>", master_doc_path="<parent task.json>", subtask_number="<N>", dry_run=true)

Read the full file on GitHub · 564 lines

Changes

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.

  1. 1mo ago Changed · +4 lines afa1d5a58f56
  2. 1mo ago Changed · +213 lines a59923cf1be1
  3. 2mo ago First seen · 347 lines · 42 tokens per session scan A ca5fe7d176ad

Subscribe to this mod's changes

c-09-git-worktree-manager is a skill published in the GitHub repository Foxfire1st/agents-remember (39 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 8,760 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.

Related

c-09-git-worktree-manager compared with skills from other repositories

c-09-git-worktree-manager next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
c-09-git-worktree-managerFoxfire1st/agents-rememberSkill39yesterdayMITA42Claude Code, Codex
github-release-managementruvnet/RuViewSkill103kyesterdayMITA27Claude Code
agent-framework-py-releasemicrosoft/agent-frameworkSkill15kyesterdayMITA102Claude Code, Codex
atmos-hookscloudposse/atmosSkill1.4kyesterdayApache-2.0A46Claude Code
atmos-gitcloudposse/atmosSkill1.4kyesterdayApache-2.0A82Claude Code
atmos-procloudposse/atmosSkill1.4kyesterdayApache-2.0A38Claude Code
release-notes-checkascending-llc/jarvis-registrySkill3.8kyesterdayApache-2.0A16Claude Code