Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Context Pull

ASecurity

Use before starting a non-trivial coding task to gather the relevant repository context (README, docs, ADRs, related modules, recent git history) and distill it into a short working brief so the agent starts grounded instead of guessing. Triggers on "pull context", "get me up to speed", "brief before I start", "gather context".

2 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agentsgotestinggit

Security Analysis

A100/100

Scanned 10/1/2026

$npx -y skills add matthews-wong/claude-code-plugins --skill context-pull --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Context Pull?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Context Pull
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/matthews-wong-context-pull/badge)](https://www.skillsdirectory.com/skills/matthews-wong-context-pull)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: context-pull
description: 'Use before starting a non-trivial coding task to gather the relevant repository context (README, docs, ADRs, related modules, recent git history) and distill it into a short working brief so the agent starts grounded instead of guessing. Triggers on "pull context", "get me up to speed", "brief before I start", "gather context".'
---

# Context Pull

The goal is to spend a small, bounded amount of effort up front so that the
actual work is done with accurate context instead of assumptions. This mirrors
Cherny's Step 2 (pull the right context in) feeding Step 3 (act on it).

## Method

### 1. Read the map before the territory
- Root `README.md` — purpose, stack, how to build/run/test.
- `CLAUDE.md` (root and any nested) — project-specific rules that override defaults.
- `docs/` — architecture, design notes, runbooks.
- ADRs — look in `docs/adr/`, `.harness/adrs/`, or `adr/`. These record *why*
  hard-to-reverse decisions were made; honor them.

### 2. Narrow to the task's blast radius
- Use glob to find candidate files by name (e.g. the feature/domain keyword).
- Use grep to find where a symbol, route, or config key is defined and used.
- Read the handful of files that are clearly central. Skim the periphery — you
  need enough to act correctly, not a full audit.

### 3. Pull recent history for signal
- `git log --oneline -20` for overall momentum.
- `git log --oneline -10 -- <path>` for the specific area.
- Recent churn often points at the code you are about to touch and at bugs.

### 4. Capture conventions and gotchas
Note naming, layering, error-handling, and testing patterns actually used in the
files you read — match the code over any external preference.

## Output: the Working Brief

Produce a single concise brief (aim for one page):

- **Goal** — the task restated in repository terms.
- **Relevant files** — path + one-line role each.
- **How it fits together** — control/data flow in a short paragraph.
- **Conventions to honor** — observed style/architecture/testing rules.
- **Recent activity** — notable recent commits in the area.
- **Open questions / risks** — ambiguities and likely traps.

## Bounds and follow-through
- Time-box the gather. If you have read ~5-10 files and the picture is clear,
  stop and write the brief.
- Do not begin implementation while gathering — separate the phases so the brief
  stays honest.
- Once confirmed accurate, offer to persist the stable parts (conventions,
  architecture summary) into `CLAUDE.md` so future sessions start grounded.

Attribution

matthews-wongmatthews-wong
View sourceSee grades on GitHubMore from matthews-wong →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →