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 instructions/jackchuka/skillctx/claude-mdgit clone --depth 1 https://github.com/jackchuka/skillctxWhat 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 | $0.00405 | $0.00405 |
| Opus 5 | $0.00202 | $0.00202 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
skillctx CLAUDE.md 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 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.
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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
uv sync --dev # Install dependencies
uv run pytest # Run all tests
uv run pytest tests/test_resolve.py -k test_name # Run a single test
uv run ruff check . # Lint
uv run ruff format . # Format
uv run mypy . # Type check
uv run python scripts/sync-version.py # Sync version from pyproject.toml to SKILL.md + marketplace.json
Architecture
This skill should work with any agent host that can run Python scripts and supports the agentskills.io skill format.
skillctx makes agent skills portable by extracting hardcoded values (usernames, paths, channel IDs) into a central config file (~/.config/skillctx/config.json) and embedding a resolver script into each skill.
Config structure: vars holds shared values organized by category (identity, slack, paths, blog). skills maps each skill name to bindings — key-to-dotpath mappings that reference values in vars.
Two skills in skills/:
- skillctx-ify — Migrates a skill: scans for hardcoded values (Phase 1, deterministic), classifies candidates with LLM judgment (Phase 2), then rewrites files and embeds the resolver (Phase 3).
- skillctx-sync — Bulk-updates the embedded resolver script across all previously migrated skills when
resolve.pychanges.
Conventions
resolve.pymust stay zero-dependency (Python 3.10+ stdlib only) — it gets embedded into other repos- Ruff config: line-length 100, target py310, rules E/F/I/UP/B/SIM/RUF
- mypy strict mode enabled; tests exempt from
disallow_untyped_defs
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 · 35 lines · 405 tokens per session scan A d2b60e48addf
skillctx CLAUDE.md is an instructions file published in the GitHub repository jackchuka/skillctx (5 stars, last pushed 15d ago), licensed MIT. It adds 405 tokens to every session, about $0.0020 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 2026-08-31.
Other instructions, from other repositories
neo-chat AGENTS.md
AGENTS.md instructions for u14app/neo-chat, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
gemini-watermark-remover AGENTS.md
Instructions for GargantuaX/gemini-watermark-remover, covering agents.md, best-effort product principle, debug workflow, allenk upstream reference and data-driven watermark investigation.
anti-sycophant-ai-agent-skills AGENTS.md
Instructions for machinesoul11/anti-sycophant-ai-agent-skills, covering agents.md, what this repo is, repo layout, rules for agents editing this repo and how the skills are meant to fire.
anti-sycophant-ai-agent-skills CLAUDE.md
Instructions for machinesoul11/anti-sycophant-ai-agent-skills, covering anti-sycophant, what's in here, conventions and when working in this repo.
antigravity-config GEMINI.md
Gemini CLI instructions for LuisSambrano/antigravity-config, covering 🧠 omni-architect agent protocol v1.0, ⚙️ core engine (prev loop), 📂 domain protocols (auto-activate based on context), 1. prompteng (prompt engineering) and 2. debug (bug hunting).
gemini-cli-skill-creator GEMINI.md
Gemini CLI instructions for involvex/gemini-cli-skill-creator, covering agent skills, key benefits, skill discovery tiers, managing skills and in an interactive session.