context-engineering instructions

3,564 tagged context-engineering, measured the same way as everything else here.

Browse within: agent-memory 31copilot 26ai-coding-assistant 22github-copilot 20ai-guardrails 19contextops 19codex-cli 15coding-agents 15prompt-engineering 15agents-md 13ai-memory 11antigravity 10coding-agent 9context 9

architect

265

bonigarcia/context-engineering

Agent

Keep the solution inside a single Python module with one immutable data structure and one scoring function. Reject invalid numeric values before computing the score.

132 4d ago A 0 tokens original Apache-2.0

developer

266

bonigarcia/context-engineering

Agent

Implement Idea and scoreidea in src/backlog.py, and verify them with tests/testbacklog.py. Use the formula impact 5 + strategicfit 3 - effort 2.

132 4d ago A 0 tokens original Apache-2.0

product-manager

267

bonigarcia/context-engineering

Agent

Add an idea-score capability so the backlog assistant can rank candidate work with a simple, transparent score based on impact, effort, and strategic fit.

132 4d ago A 0 tokens original Apache-2.0

colin AGENTS.md

269

PrefectHQ/colin

Instructions file CodexOpenCode

AGENTS.md instructions for PrefectHQ/colin, a project described as: A context engine that treats skills as software.

121 27d ago A 4 tokens

colin CLAUDE.md

270

PrefectHQ/colin

Instructions file

Claude Code instructions for PrefectHQ/colin, covering colin development guidelines, required development workflow, documentation requirements, user-facing documentation (docs/) and docs/architecture.md.

121 27d ago A 755 tokens

models

271

PrefectHQ/colin

Skill Claude CodeCodex

Skill "models" from PrefectHQ/colin, covering running tools and tools.

121 27d ago A 0 tokens

intent-driven-dev/intent-driven-template

Skill Claude CodeCodex

Use when creating or modifying acceptance tests, configuring cucumber-js or behave runners, writing or refactoring step definitions, linting executable Gherkin specs, choosing an acceptance stack, or implementing OpenSpec tasks that involve acceptance tests.

121 9d ago A 51 tokens original MIT

gherkin-authoring

273

intent-driven-dev/intent-driven-template

Skill Claude CodeCodex

Use when drafting, reviewing, or improving Gherkin, Cucumber scenarios, BDD acceptance criteria, feature examples, Scenario Outlines, Backgrounds, Rules, Doc Strings, Data Tables, tags, or Gherkin embedded in Markdown.

121 9d ago A 54 tokens original MIT

intent-driven-dev/intent-driven-template

Instructions file CodexOpenCode

Instructions for intent-driven-dev/intent-driven-template, a project described as: OpenSpec and OpenCode template for intent-driven development with specs, ADRs, C4 diagrams, Gherkin, TDD, Multi-Model Adversarial Spec Authoring, Glossary for Domain Terms, and reusable engineering workflows. This also makes OpenSpec…

121 9d ago A 42 tokens original MIT

tiger-cli CLAUDE.md

279

timescale/tiger-cli

Instructions file

Instructions for timescale/tiger-cli, covering claude.md, naming guidelines, official names, examples and development commands.

116 5d ago A 13,873 tokens original Apache-2.0

tiger-cli

280

timescale/tiger-cli

MCP server Claude CodeCodexCursor +2

MCP server "tiger-cli" as configured in timescale/tiger-cli. Runs in Docker (ghcr.io/timescale/tiger-cli:0.22.0). Needs 2 environment variables to run.

116 5d ago A tokens not measured original Apache-2.0

open-index CLAUDE.md

281

DrDroidLab/open-index

Instructions file

Instructions for DrDroidLab/open-index, covering open index repository guidance and public-safety rules.

105 21d ago A 131 tokens original MIT

edit-brain

282

DrDroidLab/open-index

Skill Claude CodeCodex

How to add or edit knowledge in this brain — define doctypes, add or update entities, and correlate them with relationships. Use whenever the user asks to add/update knowledge, define a concept, record a learning, or link two things in the brain.

105 21d ago A 55 tokens original MIT

setup-open-index

283

DrDroidLab/open-index

Skill Claude CodeCodex

Install and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP.

105 21d ago A 48 tokens original MIT

SessionStart

284

gintasz/unigent

Hook Claude Code

Runs when a session starts on startup, executing worktree-bootstrap.sh via bash. From gintasz/unigent.

104 1mo ago A tokens not measured original MIT

unigent

285

gintasz/unigent

Settings file Claude Code

Agent settings declaring 1 hook event (SessionStart).

104 1mo ago A tokens not measured original MIT

unigent AGENTS.md

286

gintasz/unigent

Instructions file CodexOpenCode

Instructions for gintasz/unigent, covering setup — do this first in any fresh checkout or worktree, core vs. adapter, constitution, validation and releases.

104 1mo ago A 550 tokens original MIT

unigent CLAUDE.md

287

gintasz/unigent

Instructions file

Instructions for gintasz/unigent, a project described as: Build stateful agent workflows with typed outputs, reusable tools, session forks, and ordinary TypeScript.

104 1mo ago A 3 tokens copy · 100% MIT

herry2059/project-os-for-codex

Instructions file CodexOpenCode

Instructions for herry2059/project-os-for-codex, covering ai contributor rules, product truth, architecture and security, development workflow and agent integration contract.

101 1mo ago A 656 tokens original Apache-2.0

At most 3 mods per repository are shown here — the rest are on their repository pages: