Entire skills

Skills for searching past work in Entire history: checkpoints, sessions and git history explain code and hand a task to another agent

  • 239 ★ on the repository
  • Last commit
  • MIT
SkillOfficial

Extended access

Why this level

  • Transcripts of past sessions contain prompts and sometimes secrets, and the agent reads them into context
  • Search over indexed history goes through the Entire service after `entire login`
  • `session-crosslink` rewrites the latest commit via amend, though only after confirmation
All reasons and checks

entireio/skills

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/entire-skills

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Transcripts of past sessions contain prompts and sometimes secrets, and the agent reads them into context
  • Search over indexed history goes through the Entire service after `entire login`
  • `session-crosslink` rewrites the latest commit via amend, though only after confirmation

This is third-party code. Review the repository files before installing.

What it does

Entire skills teach an agent to use the context that Entire CLI records: prompts, transcripts, checkpoints and decisions stored next to git history. Instead of memorizing commands you ask in plain language: "search past work for rate limiting", "explain src/auth.ts", "hand off this session". The `search` skill finds prior work by topic, repository, branch, author or period, and fires as the first action on "research" and "investigate" requests, before reading files or grep. `explain` finds the session behind a function, file or line and recovers the requirement and decision. `what-happened` starts from an exact line or snippet and traces the latest change through `git blame` and checkpoint context. `review` audits a branch from transcripts with the author's intent in mind and reports findings at Critical, High, Medium and Low levels compatible with `entire review --fix`. `session-handoff` passes task state to another agent, `session-to-skill` turns repeated work into a new skill, `session-crosslink` attaches a session run elsewhere to the right repository's commit, and `using-entire` routes a request to the fitting one.

Who it is for. Teams that run repositories with Entire and want the agent to know why code was written the way it was and to pick up someone else's session.

Good fit when

  • Before changing a migration, the agent has to find what was already tried and why it was dropped
  • A function in `src/auth.ts` is unclear and you need the original task statement rather than guesses from the code
  • A branch is about to be merged and the review should account for what the author wanted in the agent conversation
  • Codex started the work and Claude Code continues, and the task state with blockers must pass over without a retelling
  • A recurring process such as preparing release notes is ready to become a skill

Not a fit when

  • You need to record context rather than search it: Entire CLI creates the checkpoints and the skills only read them
  • You need search across the local history of different agents without tying it to commits: Coding Agent Session Search (cass) does that
  • You only want a diff review without the conversation: the `review` skill builds its conclusions on checkpoint transcripts and is thinner without them

Example request

search past work for rate limiting

Limitations

The skills need Entire CLI installed and a repository where Entire has recorded sessions or checkpoints. Searching indexed history requires `entire login`, and remote results need a GitHub origin and pushed, indexed checkpoints. A new or lightly covered repository yields few findings. On macOS in Codex, `entire` commands have to run with escalated sandbox permissions because the sandbox cannot reach the local credential store.

How to disable. In Claude Code run `/plugin uninstall entire`. If you cloned the repository into `~/.agents/skills/entire` or `~/.cursor/skills/entire`, delete that folder. Entire CLI itself and the checkpoints it recorded stay.

FAQ

How do I install just the search skill?

Run `npx skills add https://github.com/entireio/skills --skill search`. You can add the other skills later with the same `--skill` flag and their names.

How do I make search the agent's first step?

The `search` and `using-entire` descriptions already claim the verbs "research" and "investigate". For a guarantee, add a line to `CLAUDE.md` or `AGENTS.md` saying such requests start with `entire search "<topic>" --json --compact --limit 5`: user instructions outrank skill descriptions in agents.

How does `what-happened` differ from `explain`?

`explain` answers why a function, file or line exists and which requirement stands behind it. `what-happened` takes a concrete block and shows what changed in it last, through `git blame` and the checkpoint.

Does `session-crosslink` work without confirmation?

No, it first shows the plan with `--dry-run` and amends the commit only after you agree. The skill is for sessions run outside the repository: from a higher folder, from a repo without Entire, or while editing another repo.

Which agents do the skills work in?

The README has installation for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode. Codex and OpenCode pick skills up from `~/.agents/skills/`, Cursor from `~/.cursor/skills/`, and Gemini CLI installs them with `gemini extensions install`.

Discussion

No questions or reviews yet.

Skills

A set of independent skills against drift in large codebases: hard-cut, root-cause tracing, lean testing and CI right-sizing.

SkillMinimal access139Repository stars

Nine JS Mastery skills take a change through phases: from idea and spec to verification, tests, release texts and a docs sync

SkillExtended access1.6KRepository stars

14 skills that find the gaps in a task before the code: interviews, plans, assumption tests and proof that a bug fix works

SkillMinimal access363Repository stars

Builder Skills

Skills for agents

A set of small skills from Builder.io for agent work habits: visual plans and diff recaps, docs-first checks, cross-agent review and clean status updates

SkillExtended access4.6KRepository stars

An autonomous iteration skill for agents: modify, verify, revert failed changes, and repeat the loop toward a target metric

SkillBroad access6.8KRepository stars

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialRepository starsMain difference
Entire skills (this card)yes239
Entire CLIno5,314the CLI that records sessions and checkpoints, while these skills teach the agent to search and explain from them
Coding Agent Session Search (cass)no1,201searches the local session history of different agents, while Entire skills rely on checkpoints tied to commits

README in short

The README explains why the repository exists: Entire CLI records the context behind changes and the skills teach agents to use it. Then come installing all skills or one, example prompts, a table of tasks, a description of each skill and install steps for six agents.

README badge

Original SKILL.md

---
name: search
description: Use when the user asks to research, investigate, look into, dig into, or search for anything — a topic, feature, bug, decision, or "what do we know about X". Invoke this as the FIRST action on such requests, before Glob, Grep, or Read: the answer is in Entire's recorded history (prompts, transcripts, and decisions, across repos), not in the local files, and a working copy that looks empty or unfamiliar is not a reason to skip it. Also use to find code across repositories ("where is X implemented in our other repos"). Not for grepping the current working copy on its own, and not for the current active session.
---

# Search Checkpoints and Code

Use `entire search` to find prior checkpoints, commits, and sessions with hybrid (semantic + keyword) search, or `entire search --code` to search code content across repositories. Requires `entire login`. Never run `entire search` without `--json` — it opens an interactive TUI.

## Search First

When the user asks to research, investigate, look into, or dig into something, the first action is one `entire search` call, before reading source files or running grep. Recorded prompts, transcripts, and decisions answer "what has been tried and why" in a way code cannot. Grep and file reads come after, to confirm what the history says. Fall back to code-only reasoning only when search returns nothing, and say so.

## Execution Environment

On macOS, `entire` reads credentials from the local secrets store, which the Codex sandbox cannot reach. In Codex, run every `entire` command with `sandbox_permissions: "require_escalated"` on the first attempt (justification: needs the user's local Entire credentials). A sandboxed credential error is not evidence the user needs to log in; only report that after an unsandboxed attempt says so.

## Response Format

Begin the first response to this skill invocation with the line:

`Entire Search:`

followed by a blank line, then the content.

- Apply the header to the **first response of the invocation only.** Do not re-print it on follow-up turns within the same invocation (e.g. after the user answers a clarifying question).
- Do **not** include the header on error or early-exit responses (e.g. "Entire CLI not installed", "authentication required", "no matches"). The header's presence should signal that the skill ran and produced real output.

## When to Use

- The user says "research X", "investigate X", "look into X", "dig into X", "search for X", "find out how X works", or "what do we know about X"
- The user asks "have we done this before?", "search past work", "find the previous implementation", or "look for checkpoints about X"
- You need prior context from another branch, repo, author, or recent time period
- You are about to read code to understand a feature, bug, or decision and no one has checked the recorded history yet
- The user wants to find code across repositories they have access to, e.g. "where is X implemented?", "find usages of Y in our other repos" — use code search (`--code`)

Do not use this for the current active session; use `session-handoff` for that. Use grep or ripgrep instead of code search only when the user wants matches in the files of the current working copy and is not asking about history, intent, or other repos.

## Process

1. Run a focused search with compact JSON output:

```bash
entire search "<query>" --json --compact --limit 5
```

Report a problem

Foxx AIEntire skills
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.