A command for downloading the latest changes for the current Git branch and shared project memory. A Git branch is a separate line of work in a code repository.

Use it to sync a branch, retrieve recent repository changes, and update shared memory.

It brings your local work up to date when you need new changes without also asking to review recent activity.

pull — Skill for Claude Code and Codex by egregore-labs: A command for downloading the latest changes for the…

Install

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.

agentmods

npx agentmods add skills/egregore-labs/egregore/pull

Any agent

npx skills add egregore-labs/egregore --skill pull

Clone the repo

git clone --depth 1 https://github.com/egregore-labs/egregore

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/egregore-labs/egregore/pull.svg)](https://agentmods.dev/skills/egregore-labs/egregore/pull)

Your own site

<a href="https://agentmods.dev/skills/egregore-labs/egregore/pull"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/pull.svg" alt="Measured on agentmods" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,209 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00028	$0.01209
Opus 5	$0.00014	$0.00605
Sonnet 5	$0.00006	$0.00242
Haiku 4.5	$0.00003	$0.00121

Measured 5d ago against content hash a6bc53933320, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pull 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.

.claude/skills/pull/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pull latest for current repo and shared memory.

Note: /activity auto-syncs. Use /pull only when you need to sync without viewing activity.

When to invoke

User says: "/pull", "pull latest", "sync my branch", "get the latest changes", "update memory", or needs to sync without also viewing activity. Not this: also want to see recent activity → /activity (auto-syncs already).

Loom routing

Skip this section if your prompt contains LOOM-EXECUTOR — you are the executor; run the skill as specced below. Full protocol: .claude/context/loom.md.

Resolve: ROUTE=$(bash bin/loom.sh route pull), then DECISION_ID=$(printf '%s\n' "$ROUTE" | jq -r '.decision_id // empty').
If mode ≠ delegate, or the user signalled depth ("deep", "think hard", --deep) → run this skill inline as normal. On a depth override, print bash bin/loom.sh footer pull --override after the output and set "override":true in telemetry.
Otherwise delegate: spawn the Agent tool with subagent_type: "loom-executor", model = the route's tier, prompt = LOOM-DECISION-ID: $DECISION_ID on its own first line, then LOOM-EXECUTOR: Execute .claude/skills/pull/SKILL.md, plus the user's arguments and any context the spec needs from the session. Print the executor's final output verbatim, then print the output of bash bin/loom.sh footer pull.
If the spawn fails or the executor's first line is LOW_CONFIDENCE: — triage the reason: needs-user-interaction or a main-loop-only tool → take over and finish this skill inline (no escalation); genuine uncertainty or failure → reassign ROUTE=$(bash bin/loom.sh escalate pull "<reason>"), refresh DECISION_ID from ROUTE, then re-spawn once on the new tier carrying the returned decision ID (sticky for this session).
Telemetry (fire-and-forget): bash bin/telemetry.sh emit "command" '{"command":"pull","routed":true,"mode":"delegate","model":"<actual>","route_tier":"<table tier>","class":"<class>","escalated":<bool>,"override":<bool>,"source":"<source>"}' 2>/dev/null &

Read the full file on GitHub · 97 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.

5d ago First seen · 97 lines · 28 tokens per session scan A a6bc53933320

Subscribe to this mod's changes

pull is a skill published in the GitHub repository egregore-labs/egregore (280 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,209 once invoked, about $0.0001 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.

Collaboration Git and workflow Memory and context ai claude claude-code cli developer-tools

crewai-multi-agent

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…

davila7/claude-code-templates · 61 tokens

company-kb

Use when company-kb — Company Knowledge Base Skill. Use when relevant to this domain.

oyi77/1ai-skills · 22 tokens

crewai-multi-agent

OpenLAIR/dr-claw · 61 tokens

crewai-multi-agent

synthetic-sciences/openscience · 61 tokens

checkpoint

Generate a session handover document and save it to disk so the session can be resumed after /clear. Use when wrapping up a session, before a context reset, or when the user asks to checkpoint / save progress for a fresh session.

toBzh30/Claude-Project-Bootstrap · 50 tokens

know-me

Collaboration-profile interview that creates or refreshes a reusable AI Collaboration Manual. Use when the user invokes Know Me ($know-me or /know-me), chooses first use, quick start, or deep calibration, asks for an AI collaboration manual, provides an existing manual to update, wants stable long-term collaboration…

doublesq97-ui/know-me · 97 tokens

pull

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

When to invoke

Loom routing

What this file has done since we first saw it

Other skills, from other repositories

crewai-multi-agent

company-kb

crewai-multi-agent

crewai-multi-agent

checkpoint

know-me