Agent skill

Agent Wiki Consult

by AgentToolkit in AgentToolkit/altk-evolve

Has the agent read a project wiki's AGENTS.md and pull the guidelines that fit the task it is about to start, instead of loading the wiki at session start.

Apache-2.0Auto-check passedAgent Workflows

Install Agent Wiki Consult

skills CLI
$ npx skills add AgentToolkit/altk-evolve --skill agent-wiki-consult -a claude-code

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

GitHub CLI
$ gh skill install AgentToolkit/altk-evolve agent-wiki-consult --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/AgentToolkit/altk-evolve.git skills-src && mkdir -p .claude/skills && cp -r skills-src/explorations/agent-wiki/skills/agent-wiki-consult .claude/skills/agent-wiki-consult && 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
agent-wiki-consult
GitHub stars
122
Token cost
~1.1k tokens
SKILL.md length
586 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
Apache-2.0

At a glance

Has the agent read a project wiki's AGENTS.md and pull the guidelines that fit the task it is about to start, instead of loading the wiki at session start.

  • Works in 5 steps: Resolve the wiki root → Read AGENTS.md → Read the retrieval index → …
  • Starting a block of work in an area a project wiki may already document
  • SKILL.md covers Overview, When to invoke, Workflow and Args, plus 1 more section
  • Calls uv

What it does

The wiki holds evidence-grounded guidelines distilled from earlier agent trajectories, and its own `AGENTS.md` explains how to navigate and query it. This skill is a thin wrapper that points the agent at that file, so retrieval rules can change in `AGENTS.md` without touching the skill.

The agent first finds the wiki root, either from a path you pass or by walking up from the working directory to the nearest `wiki-*` folder containing `_config.yaml`, and asks you if none turns up. It then reads `AGENTS.md`, building the catalog with a bundled `build_agent_wiki.py` script through `uv run` if the file is missing, reads `_index.jsonl`, and follows the retrieval recipe using tags and keywords from the task. Use it once a plan exists or a new sub-task appears, not for typo fixes or one-line edits.

When your agent uses it

  • Starting a block of work in an area a project wiki may already document
  • A new sub-task appears mid-session, such as handling browser auth resumption
  • Before writing non-trivial code that the wiki's guidelines might cover

Example prompts

  • “Consult the wiki-twobatch guidelines before you implement the retry logic.”
  • “Check the agent wiki for anything relevant to resuming browser auth.”
  • “We are about to refactor the export module, so look up the wiki guidance first.”

Requirements

  • A wiki directory named wiki-* with `_config.yaml` and `AGENTS.md`
  • `uv`, to rebuild the catalog when AGENTS.md is missing

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Resolve the wiki root
  2. Read AGENTS.md
  3. Read the retrieval index
  4. Apply the recipe from AGENTS.md
  5. Surface the matches

What it can do on your machine

Read from SKILL.md and the folder at commit 9e5bb56. 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

    Shell commands in SKILL.md call:

    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    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

Agent Wiki Consult loads about 1.1k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 586 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 AgentToolkit/altk-evolve at commit 9e5bb56, republished under its Apache-2.0 licence (© AgentToolkit). 586 words, ~1,081 tokens.

Download SKILL.mdSave it as .claude/skills/agent-wiki-consult/SKILL.md (or your agent's skills folder).
name
agent-wiki-consult
description
Consult an agent-wiki for guidelines relevant to the task at hand. The wiki itself documents how to retrieve from it (AGENTS.md). Use this skill once you know what task or sub-task you're about to do — not at session start.

Agent Wiki — Consult

Overview

This skill is a thin wrapper around the wiki's own AGENTS.md document. The wiki contains evidence-grounded guidelines distilled from agent trajectories; AGENTS.md is its agent-readable contract for navigation and retrieval. This skill tells you to:

  1. Find the wiki root.
  2. Read <wiki-root>/AGENTS.md.
  3. Follow the recipe described there against the user's current task.

The retrieval logic lives in AGENTS.md, not in this skill. That separation is intentional: when the wiki's structure or recall heuristics change, edit AGENTS.md and not this skill.

When to invoke

Call this skill once you know the task or sub-task you're about to do. Concretely:

  • After the user has stated their request and you have a plan for the next block of work.
  • Before writing non-trivial code in a problem space the wiki may have documented.
  • Mid-task when a new sub-task emerges with its own narrow scope (e.g. "now I need to handle browser auth resumption").

Do not invoke at session start (no task to filter against), and do not invoke for trivial tasks (typo fix, single-line edit) where the wiki's overhead exceeds the work.

Workflow

Step 1: Resolve the wiki root

If the user passed a path argument (e.g. wiki-twobatch, wiki-twobatch-skills, or any other path), use it.

Otherwise auto-detect: walk up from the current working directory looking for any sibling directory matching wiki-* that contains an _config.yaml file. If multiple are found, prefer the one closest to cwd. If none are found, ask the user which wiki to consult.

Step 2: Read AGENTS.md
Read <wiki-root>/AGENTS.md

This is the contract document. It explains the wiki's structure, the filename suffix convention, the _index.jsonl schema, and a recommended retrieval recipe. Read it in full — it's typically 3–5 KB.

If the file does not exist, run:

bash
uv run python explorations/agent-wiki/skills/scripts/build_agent_wiki.py \
  --wiki-root <wiki-root> catalog

Catalog's bootstrap phase will copy the bundled template into place.

Step 3: Read the retrieval index
Read <wiki-root>/_index.jsonl

One row per guideline / cluster / task / subtask. Schema documented in AGENTS.md. Rows are sorted clusters-first.

Show full SKILL.md (265 more words)Show less
Step 4: Apply the recipe from AGENTS.md

Per the recipe in AGENTS.md (which is advisory, not mandatory):

  1. Identify topical tags + keywords from the task description.
  2. Filter _index.jsonl rows by tag overlap or trigger: substring match.
  3. Prefer cluster rows when a cluster and its members both match.
  4. Read the top 2–5 matching pages in full.
  5. State which guidelines apply (briefly) before acting on them.

Use your judgment for scoring. The wiki does not prescribe a fixed algorithm; trust the heuristics in AGENTS.md and the row content.

Step 5: Surface the matches

Report 2–5 candidate matches to the user (or to your own next-step reasoning) with:

  • Title
  • One-line summary
  • Relative path inside the wiki
  • Tags
  • Why this match scores high (one phrase)

Args

This skill accepts:

  • An optional path to the wiki root. Examples: wiki-twobatch, wiki-twobatch-skills, or an absolute path.
  • An optional task description. If omitted, infer from the conversation context.

Best practices

  1. Don't pre-load. This skill is on-demand by design. Calling it at session start without a specific task wastes tokens and produces noise.
  2. Read AGENTS.md every time. Wikis evolve; the contract may have changed. Caching the contract across invocations is fragile.
  3. Read clusters before atomics. Cluster pages reference their members — you usually don't need to read the members directly.
  4. Cite when you act on a guideline. Mention the guideline's title + link in your response so the user can audit the recommendation.
  5. Don't follow guidelines blindly. If a guideline's trigger: doesn't quite match your situation, say so — note the close match and choose your own course.

© AgentToolkit, 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 explorations/agent-wiki/skills/agent-wiki-consult of AgentToolkit/altk-evolve.

Open the folder on GitHubat commit 9e5bb56

Compare with similar skills

Agent Wiki Consult 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.

Agent Wiki Consult compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Wiki Consult this skillAgentToolkit/altk-evolve122—~1.1kAutomated safety check: PassApache-2.0
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
SkillOpt Sleep Cyclemicrosoft/SkillOpt18k—~2.3kAutomated safety check: PassMIT
CLAUDE.md Improveranthropics/claude-plugins-official37k5 repos~1.5kAutomated safety check: PassApache-2.0
Harness Engineering10xChengTu/harness-engineering1021 repos~1kAutomated safety check: PassNone
Codebase Analyzerseverity1/claude-code-auto-memory159—~1.5kAutomated safety check: PassMIT

Similar skills

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • CLAUDE.md Improver

    anthropics/claude-plugins-official

    Official

    Finds every CLAUDE.md file in a repository, scores each against quality criteria, shows a report, then makes targeted updates after you approve.

    37k GitHub starsUsed in 5 repos~1.5k tokens
    Agent WorkflowsAuto-check passed
  • Harness Engineering

    10xChengTu/harness-engineering

    Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.

    102 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check passed
  • Codebase Analyzer

    severity1/claude-code-auto-memory

    This skill should be used when the user asks to "initialize auto-memory", "create CLAUDE.md", "set up project memory", or runs the /auto-memory:init command.

    159 GitHub stars~1.5k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed
  • Self Improving For Codex

    GODGOD126/self-improving-for-codex

    Build or maintain a Codex-native self-improving memory loop using global AGENTS.md, a persistent memories directory, and optional nightly refinement automation.

    130 GitHub stars~1.2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

More from AgentToolkit/altk-evolve

All 21 skills in this repo
  • Agent Wiki Compare Outcomes

    AgentToolkit/altk-evolve

    Contrasts successful and failed agent runs of the same task and derives guidelines backed by evidence from transcripts, tool calls and outcome judgments.

    122 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Trajectory Skill Synthesizer

    AgentToolkit/altk-evolve

    Turns a saved agent trajectory into a reusable skill with a SKILL.md and supporting scripts, so later sessions can call the workflow instead of rediscovering it.

    122 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Evolve Memory Mirror

    AgentToolkit/altk-evolve

    Copies a memory the agent just saved into the shared evolve store with a retrieval trigger, so it can be shared across a team and audited like other entities.

    122 GitHub stars~922 tokensUpdated today
    Auto-check passed
  • Agent Wiki Guideline Extractor

    AgentToolkit/altk-evolve

    Reads a normalized Claude Code trajectory JSON and turns its errors and solutions into reusable guideline pages in wiki-twobatch/guidelines.

    122 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Agent Wiki Ingest

    AgentToolkit/altk-evolve

    Ingest one or more agent trajectories (raw bob/claude traces or normalized JSON) into an agent-wiki end-to-end — convert, summarize, extract guidelines, synthesize skills, optionally compare…

    122 GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Agent Wiki Summarize

    AgentToolkit/altk-evolve

    Read a normalized Claude Code trajectory JSON and write an episodic summary page to wiki-twobatch/summaries/.

    122 GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Categories

Questions about Agent Wiki Consult

What does Agent Wiki Consult do?

Has the agent read a project wiki's AGENTS.md and pull the guidelines that fit the task it is about to start, instead of loading the wiki at session start. md` explains how to navigate and query it.md` without touching the skill.

When should I use Agent Wiki Consult?

Agent Wiki Consult fits situations like: starting a block of work in an area a project wiki may already document; A new sub-task appears mid-session, such as handling browser auth resumption; before writing non-trivial code that the wiki's guidelines might cover.

How do I install Agent Wiki Consult in Claude Code?

Run `npx skills add AgentToolkit/altk-evolve --skill agent-wiki-consult -a claude-code`. Or copy the skill folder (explorations/agent-wiki/skills/agent-wiki-consult in AgentToolkit/altk-evolve) into .claude/skills/agent-wiki-consult in your project. Claude Code loads it when a task matches its description.

How do I install Agent Wiki Consult in Codex?

Run `npx skills add AgentToolkit/altk-evolve --skill agent-wiki-consult -a codex`. Or copy the skill folder (explorations/agent-wiki/skills/agent-wiki-consult in AgentToolkit/altk-evolve) into .agents/skills/agent-wiki-consult in your project. Codex loads it when a task matches its description.

Can I use Agent Wiki Consult 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 AgentToolkit/altk-evolve --skill agent-wiki-consult -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-wiki-consult, .gemini/skills/agent-wiki-consult, .github/skills/agent-wiki-consult and .opencode/skills/agent-wiki-consult in your project.

What does Agent Wiki Consult need to run?

Going by SKILL.md and its folder, Agent Wiki Consult needs the command-line tools its instructions call (uv). Our summary lists: A wiki directory named wiki-* with `_config.yaml` and `AGENTS.md`; `uv`, to rebuild the catalog when AGENTS.md is missing.

Does Agent Wiki Consult access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Agent Wiki Consult 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 Agent Wiki Consult use?

Agent Wiki Consult is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Wiki Consult use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Agent Wiki Consult?

Skills that share tags, products or a category with Agent Wiki Consult: Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), SkillOpt Sleep Cycle (microsoft/SkillOpt, 18k stars), CLAUDE.md Improver (anthropics/claude-plugins-official, 37k stars) and Harness Engineering (10xChengTu/harness-engineering, 102 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Wiki Consult?

AgentToolkit (a GitHub organization) maintains it in AgentToolkit/altk-evolve, which has 122 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.

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