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.
npx agentmods add skills/fending/context-engineering/context-mcpnpx skills add fending/context-engineering --skill context-mcpgit clone --depth 1 https://github.com/fending/context-engineeringWhat 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 | $0.00042 | $0.03429 |
| Opus 5 | $0.00021 | $0.01715 |
| Sonnet 5 | $0.00008 | $0.00686 |
| Haiku 4.5 | $0.00004 | $0.00343 |
Grade B, and why
context-mcp scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Claude Code | `~/.claude/settings.json` | JSON | How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DEPRECATION NOTICE: You are running context-setup from fending/context-engineering, which is no longer maintained. The active version is at ordovera/ordovera-plugins. To migrate, run:
/plugin marketplace add ordovera/ordovera-plugins/plugin install context-setup@ordovera-plugins
Then remove the old marketplace: /plugin marketplace remove context-engineering
Print this notice to the user before proceeding with the skill.
Context MCP
Optimize MCP tool calls the same way Command Output Notes optimizes CLI commands. Detect what MCP servers are connected, match against known templates, and generate documentation that reduces token waste from default tool parameters.
General Principle: CLI Over MCP for Reads
When a CLI tool and MCP server both cover the same operation, prefer CLI for read operations. CLI tools generally offer field selection (--json field1,field2), output piping (| tail -5), and documented, predictable behavior. MCP servers typically wrap raw APIs with no field filtering -- GitHub's MCP get_issue returns ~100 lines where gh issue view --json title,state returns 1. MCP is the right choice for write operations (creating issues, sending messages) where output size doesn't matter, and for services that have no CLI equivalent.
When generating MCP Tool Notes, flag cases where a CLI alternative exists and if superior in performance recommend CLI for reads alongside the MCP optimization guidance.
What This Skill Does
Two tiers: known pattern recommendations (deterministic, config-based) and interactive discovery (user-in-the-loop, for unknown servers).
1. Detect MCP Configurations
Scan for MCP config files across platforms. Always ask before reading user-level configs outside the project directory.
Project-level configs (read without asking):
| Platform | Path | Format |
|---|---|---|
| Claude Code | .mcp.json |
JSON |
| OpenAI Codex | .codex/config.toml |
TOML |
| Gemini CLI | .gemini/settings.json |
JSON |
| VS Code / GitHub Copilot | .vscode/mcp.json |
JSON |
| Cursor | .cursor/mcp.json |
JSON |
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.
- 2d ago First seen · 232 lines · 42 tokens per session scan B 906c83aba4a8
context-mcp is a skill published in the GitHub repository fending/context-engineering (11 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 3,429 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
packmind-create-command
Guide for creating reusable commands via the Packmind CLI. This skill should be used when users want to create a new command that captures multi-step workflows, recipes, or task automation for distribution to GitLab Duo.
packmind-update-playbook
Use when updating, adding, fixing, changing, or deprecating Packmind playbook artifacts (standards, commands, skills). Triggers on explicit phrases like "update packmind standard", "add a packmind skill", "fix packmind command", "change packmind playbook", "deprecate a standard". Also triggers — even without an…
packmind-create-skill
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends GitLab Duo's capabilities with specialized knowledge, workflows, or tool integrations.
agents
Guidance for AI coding agents working on the adeptability (adept) codebase. Humans: see README.md for usage and CONTRIBUTING.md for the contributor workflow.
using-adept
Use the adept CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing/syncing skills, editing skill.yaml/SKILL.md, or touching .adeptability/.
authoring-adept-agents
Write a good, portable adept agent (subagent): trigger-shaped description, one job per agent, generator/evaluator separation, explicit boundaries, restricted tools. Apply when creating or editing an agent file or running adept agent add.