New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Autocontext Knowledge Reader

by greyhaven-ai in greyhaven-ai/autocontext

Reads and moves the playbooks and lessons that Autocontext has already learned, using the autoctx CLI and plain files on disk.

Apache-2.0Auto-check passedAgent Workflows

Install Autocontext Knowledge Reader

skills CLI
$ npx skills add greyhaven-ai/autocontext --skill autocontext-consumer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install greyhaven-ai/autocontext autocontext-consumer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/greyhaven-ai/autocontext.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/autocontext-consumer .claude/skills/autocontext-consumer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
autocontext-consumer
GitHub stars
1.3k
Token cost
~934 tokens
SKILL.md length
367 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Reads and moves the playbooks and lessons that Autocontext has already learned, using the autoctx CLI and plain files on disk.

  • Checking whether Autocontext has learned anything about a task yet
  • SKILL.md covers Overview, When to Use, Where Knowledge Lives and Reading Knowledge, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Reading the current playbook or lessons for one scenario

What it does

Autocontext stores what it learns in a knowledge directory with one folder per scenario. The skill tells the agent where that directory lives (`./knowledge` by default, or the path in `AUTOCONTEXT_KNOWLEDGE_ROOT`) and which files matter: `playbook.md` holds the current approach and is the first file to read, while `lessons.json` records how the playbook got there. Folders whose names start with an underscore are shared across scenarios.

To find out what exists, the agent uses `autoctx list`, `status` and `show` with a run ID, and `autoctx replay` to look at a single generation in detail. To carry knowledge to another checkout or machine it exports a scenario to a package file and loads it with `autoctx import-package`, choosing overwrite, merge or skip through `--conflict` and optionally renaming the scenario with `--scenario`. A missing playbook only means nothing has been learned yet. Running scenarios or judging output belongs to the separate autocontext-creator skill.

When your agent uses it

  • Checking whether Autocontext has learned anything about a task yet
  • Reading the current playbook or lessons for one scenario
  • Moving a scenario's knowledge to another checkout or machine
  • Looking into why a generation produced a surprising result

Example prompts

  • “Does Autocontext have any knowledge for the grid_ctf scenario? Show me its playbook.”
  • “Export the grid_ctf knowledge to a package so I can load it on my other laptop.”
  • “Import grid_ctf_package.json here and merge it with what is already there.”
  • “List the Autocontext runs and replay generation 1 of the latest one.”

Requirements

  • The `autoctx` CLI
  • Read access to the knowledge directory

What it can do on your machine

Read from SKILL.md and the folder at commit f72c154. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Autocontext Knowledge Reader loads about 934 tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 367 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~934

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from greyhaven-ai/autocontext at commit f72c154, republished under its Apache-2.0 licence (© greyhaven-ai). 367 words, ~934 tokens.

Download SKILL.mdSave it as .claude/skills/autocontext-consumer/SKILL.md (or your agent's skills folder).
name
autocontext-consumer
description
Use when an agent needs to USE knowledge Autocontext already produced - find which scenarios have knowledge, read the playbook and lessons for one, understand the on-disk file and folder layout, and move knowledge between checkouts. Host-agnostic; requires only the autoctx CLI and the filesystem.
version
1.0.0
author
Autocontext
license
Apache-2.0

Autocontext: Using Existing Knowledge

Overview

Autocontext writes what it learns to a knowledge directory. This skill covers reading and moving that knowledge. To produce it, use autocontext-creator.

Nothing here assumes a particular agent host, and most of it is plain file reading - the layout is documented below precisely so an agent can go straight to the file it wants.

When to Use

  • You want to know whether Autocontext has learned anything about a task.
  • You want the current playbook or lessons for a scenario.
  • You want to move knowledge from one checkout or machine to another.

Do not use this skill to run scenarios or judge output. That is autocontext-creator.

Where Knowledge Lives

The root defaults to ./knowledge and moves with AUTOCONTEXT_KNOWLEDGE_ROOT. Inside it, each scenario owns a directory:

<knowledge_root>/
  <scenario>/
    playbook.md              the current approach, rewritten as the loop learns
    lessons.json             accumulated lessons, newest last
    hints.md                 hints carried into the next attempt
    mutation_log.jsonl       one line per change, append-only
    package_metadata.json    present once the scenario has been exported
    reports/<run_id>.md      per-run written reports
  analytics/                 cross-scenario analytics
  _hub/                      shared research hub state
  _evaluator_epochs/         evaluator versioning

Directories starting with _ are shared across scenarios rather than owned by one. playbook.md is the file to read first: it is the current answer, where lessons.json is the history of how it got there.

Reading Knowledge

The playbook and lessons are plain files. Read them directly:

bash
cat "${AUTOCONTEXT_KNOWLEDGE_ROOT:-knowledge}/grid_ctf/playbook.md"

An absent file means nothing has been learned for that scenario yet. That is a normal state, not an error.

Finding Runs

bash
autoctx list --json
autoctx status "$RUN_ID" --json
autoctx show "$RUN_ID"

list is the entry point when you do not know what exists.

Show full SKILL.md (158 more words)Show less

Moving Knowledge Between Checkouts

Export a scenario's knowledge as a portable package:

bash
autoctx export --scenario grid_ctf --output grid_ctf_package.json --json

Import one somewhere else. The package file is a positional argument, not a flag, and it is required:

bash
autoctx import-package grid_ctf_package.json --json

--conflict decides what happens when the target scenario already has knowledge: overwrite, merge, or skip. --scenario imports under a different name than the package was exported from.

Use these rather than copying the directory by hand: the package carries the metadata that makes the knowledge legible on the far side.

Reading a Generation in Detail

When a result is surprising, the generation JSON is the level that explains it:

bash
autoctx replay "$RUN_ID" --generation 1

What Not to Assume

  • Knowledge is scenario-scoped. A playbook for one scenario says nothing about another.
  • lessons.json is append-only. The last entries are the newest; do not assume the file is ordered by importance.
  • An empty playbook is meaningful. It means the loop has not yet found an approach worth keeping, which is different from the scenario not existing.

© greyhaven-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/autocontext-consumer of greyhaven-ai/autocontext.

Open the folder on GitHubat commit f72c154

Compare with similar skills

Autocontext Knowledge Reader next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Autocontext Knowledge Reader compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Autocontext Knowledge Reader this skillgreyhaven-ai/autocontext1.3k—~934Automated safety check: PassApache-2.0
MemPalace Memory SearchMemPalace/mempalace59k—~1.4kAutomated safety check: PassMIT
Remember Project Knowledgezereight/gitlab-mcp2k1 repos~846Automated safety check: PassMIT
LoopX Doc Registryloopx-project/loopx6.2k—~707Automated safety check: PassApache-2.0
Context Mode Searchmksglu/context-mode26k—~250Automated safety check: PassCustom licence
Project Learnings Managergarrytan/gstack136k—~8.2kAutomated safety check: NotesMIT

Similar skills

  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    59k GitHub stars~1.4k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Remember Project Knowledge

    zereight/gitlab-mcp

    Sorts what you learned in a session into the right memory surface, filtering out ephemeral notes and duplicates before anything is stored.

    2k GitHub starsUsed in 1 repo~846 tokens
    Agent WorkflowsAuto-check passed

  • LoopX Doc Registry

    loopx-project/loopx

    Registers durable project materials such as design docs, SOPs and research notes in a LoopX project's own registry so future agents can find them without raw URLs or private content.

    6.2k GitHub stars~707 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Search

    mksglu/context-mode

    Search context-mode's persistent FTS5 knowledge base for previously indexed local project content, documentation, or session memory. Trigger…

    26k GitHub stars~250 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Project Learnings Manager

    garrytan/gstack

    Lets you review, search, prune and export the learnings gstack has collected across sessions, and surfaces them when a past fix or pattern comes up.

    136k GitHub stars~8.2k tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • Project Memory

    jamditis/claude-skills-journalism

    Generates CLAUDE.md project memory files that transfer institutional knowledge.

    417 GitHub stars~2.5k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check: notes

More from greyhaven-ai/autocontext

  • Autocontext for Hermes

    greyhaven-ai/autocontext

    Lets a Hermes agent run Autocontext scenarios, inspect Hermes curator state, export reusable knowledge and prepare local MLX or CUDA training data through the autoctx CLI.

    1.3k GitHub stars~2.5k tokensUpdated 3 days ago
    Auto-check passed

  • Autocontext

    greyhaven-ai/autocontext

    Runs LLM-based rubric judging on agent output and loops revise-and-rejudge rounds until a quality threshold is met.

    1.3k GitHub stars~892 tokensUpdated 3 days ago
    Auto-check passed

  • Autocontext Knowledge Creator

    greyhaven-ai/autocontext

    Runs the `autoctx` CLI to improve an approach to a task over several generations, score or refine a single output and inspect what a run produced.

    1.3k GitHub stars~964 tokensUpdated 3 days ago
    Auto-check passed

  • Grid CTF Strategy Playbook

    greyhaven-ai/autocontext

    Operational notes for generating, evaluating and debugging strategies in the autocontext grid_ctf scenario, with tier rules and parameter ranges that worked or failed.

    1.3k GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Autocontext Knowledge Reader

What does Autocontext Knowledge Reader do?

Reads and moves the playbooks and lessons that Autocontext has already learned, using the autoctx CLI and plain files on disk. Autocontext stores what it learns in a knowledge directory with one folder per scenario.json` records how the playbook got there.

When should I use Autocontext Knowledge Reader?

Autocontext Knowledge Reader fits situations like: checking whether Autocontext has learned anything about a task yet; reading the current playbook or lessons for one scenario; moving a scenario's knowledge to another checkout or machine; looking into why a generation produced a surprising result.

How do I install Autocontext Knowledge Reader in Claude Code?

Run `npx skills add greyhaven-ai/autocontext --skill autocontext-consumer -a claude-code`. Or copy the skill folder (skills/autocontext-consumer in greyhaven-ai/autocontext) into .claude/skills/autocontext-consumer in your project. Claude Code loads it when a task matches its description.

How do I install Autocontext Knowledge Reader in Codex?

Run `npx skills add greyhaven-ai/autocontext --skill autocontext-consumer -a codex`. Or copy the skill folder (skills/autocontext-consumer in greyhaven-ai/autocontext) into .agents/skills/autocontext-consumer in your project. Codex loads it when a task matches its description.

Can I use Autocontext Knowledge Reader in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add greyhaven-ai/autocontext --skill autocontext-consumer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autocontext-consumer, .gemini/skills/autocontext-consumer, .github/skills/autocontext-consumer and .opencode/skills/autocontext-consumer in your project.

What does Autocontext Knowledge Reader need to run?

SKILL.md names no scripts, command-line tools or credentials: Autocontext Knowledge Reader is instructions for the agent only. Our summary lists: The `autoctx` CLI; Read access to the knowledge directory.

Does Autocontext Knowledge Reader access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Autocontext Knowledge Reader safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Autocontext Knowledge Reader use?

Autocontext Knowledge Reader is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Autocontext Knowledge Reader use?

About 934 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Autocontext Knowledge Reader?

Skills that share tags, products or a category with Autocontext Knowledge Reader: MemPalace Memory Search (MemPalace/mempalace, 59k stars), Remember Project Knowledge (zereight/gitlab-mcp, 2k stars), LoopX Doc Registry (loopx-project/loopx, 6.2k stars) and Context Mode Search (mksglu/context-mode, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Autocontext Knowledge Reader?

greyhaven-ai (a GitHub organization) maintains it in greyhaven-ai/autocontext, which has 1,304 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

Source: greyhaven-ai/autocontext on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.