context-pack

A task-focused context builder that gathers the files, documents, plans, standards, and notes most relevant to upcoming coding work.

In plain words
What is it for?
Use it before large changes, code reviews, or unfamiliar work. It helps assemble a compact briefing from repository state, project notes, and other relevant sources.
Why use it?
It reduces unnecessary reading and keeps the agent focused on information that can change its next action.

Skill for Claude CodeCodex

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/lucassantana-dev/sharekit/context-pack
Any agent
npx skills add LucasSantana-Dev/sharekit --skill context-pack
Clone the repo
git clone --depth 1 https://github.com/LucasSantana-Dev/sharekit

Made for: Claude Code, Codex.

Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 467 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.

ModelPer sessionOnce invoked
Fable 5 $0.00128 $0.00467
Opus 5 $0.00064 $0.00234
Sonnet 5 $0.00026 $0.00093
Haiku 4.5 $0.00013 $0.00047

Measured 2d ago against content hash 5764b38d9381, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-pack 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.

sharekit-profile/.claude/skills/context-pack/SKILL.md · 43 lines

What it actually says

context-pack

Use before reading broadly.

Goal

Pull only the code, standards, plans, and notes that matter for the task.

Done when: context bundle complete and next read would not change action.

Preferred sources (in order)

See references/discovery-strategy.md §Preferred sources.
See also standards/user-context.md — context load order (repo state → handoff → plan → memory → standards).

Rules

See references/discovery-strategy.md §Symbol lookup strategy, §Chunking discipline, and §Anti-patterns for task-scoped retrieval rules.

Failure / Stop Conditions

  • Mount guard: If External HD unmounted → rag_query degrades; fall back to grep + claude-mem. Check before starting: mount | grep -q "${DEV_ROOT}" || echo "BLOCKED: External HD unmounted — RAG/vault unreachable".
  • If RAG retrieval returns nothing and no plans/handoffs exist for the topic → read the 2-3 most relevant files directly; do not expand the read set speculatively.
  • Stop accumulating context when the next read would not change the action — marginal reads waste budget and dilute signal.
  • Do not invoke context-pack for tasks touching one known file; direct read is faster.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 43 lines · 128 tokens per session scan A 5764b38d9381

Subscribe to this mod's changes

context-pack is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 2d ago), licensed MIT. It adds 128 tokens to every session and 467 once invoked, about $0.0006 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.