current-docs

A workflow for fetching current documentation before answering questions about libraries, frameworks, SDKs, APIs, command-line tools, cloud services, setup, or configuration. It selects relevant documentation and uses it to support the answer.

In plain words
What is it for?
Use it for questions about external technical tools or dependency upgrades. It is not intended for ordinary local refactoring or business-logic debugging.
Why use it?
Technical documentation and package behavior can change, so remembered information may be out of date. Checking current sources reduces the chance of giving obsolete instructions.

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/tam159/next-role/current-docs
Any agent
npx skills add tam159/next-role --skill current-docs
Clone the repo
git clone --depth 1 https://github.com/tam159/next-role

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 358 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 $0.00071 $0.00358
Opus 5 $0.00036 $0.00179
Sonnet 5 $0.00014 $0.00072
Haiku 4.5 $0.00007 $0.00036

Measured 2d ago against content hash dde6f8883e41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

current-docs 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.

.agents/skills/current-docs/SKILL.md · 28 lines

What it actually says

Current Docs

Use the repo's current-documentation workflow, adapted from .cursor/rules/context7.mdc.

Workflow

  1. Use Context7 for general current library, framework, SDK, API, CLI, and cloud docs.
  2. Start with resolve-library-id unless the user provides an exact /org/project Context7 ID.
  3. Choose the best library match by exact name, relevance, snippet count, source reputation, and benchmark score.
  4. Query docs with the selected library ID and the user's actual question.
  5. Query again with a narrower topic or research/deeper mode when available if the first result is thin.
  6. Answer from the fetched docs and cite the tool/source used.

Repo-Specific Docs

  • For LangChain, LangGraph, or LangSmith tasks, use docs-langchain in addition to Context7.
  • For LlamaIndex, LlamaCloud, LlamaParse, LlamaExtract, LlamaSplit, or LlamaClassify tasks, use llama-index-docs in addition to Context7.
  • Prefer MCP docs over web search for technical documentation unless the needed MCP server is unavailable or the docs are incomplete.

Boundaries

Do not use this skill for ordinary refactors, writing local scripts from scratch, reviewing local code, or debugging business logic when no external API/library behavior is in question.

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 · 28 lines · 71 tokens per session scan A dde6f8883e41

Subscribe to this mod's changes

current-docs is a skill published in the GitHub repository tam159/next-role (49 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 358 once invoked, about $0.0004 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 2026-08-30.