wayfinder

wayfinder is a skill for Claude Code, Codex from drvoss/everything-copilot-cli. It costs 47 tokens per session (1,825 once invoked), scanned A, original, MIT.

A planning method for large or unclear work that defines the desired end state before implementation. It uses an initial broad review, records deferred work, and asks for confirmation before coding starts.

In plain words
What is it for?
Use it to plan migrations, cross-cutting features, and ambiguous initiatives that need explicit scope and a shared destination.
Why use it?
It keeps long-running projects from losing direction when new questions and side issues appear. Future sessions and collaborators can follow the same agreed map.

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/drvoss/everything-copilot-cli/wayfinder
Any agent
npx skills add drvoss/everything-copilot-cli --skill wayfinder
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wayfinder

README.md
[![agentmods](https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/wayfinder.svg)](https://agentmods.dev/skills/drvoss/everything-copilot-cli/wayfinder)
Your own site
<a href="https://agentmods.dev/skills/drvoss/everything-copilot-cli/wayfinder"><img src="https://agentmods.dev/badge/skills/drvoss/everything-copilot-cli/wayfinder.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,825 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 $0.00047 $0.01825
Opus 5 $0.00023 $0.00912
Sonnet 5 $0.00009 $0.00365
Haiku 4.5 $0.00005 $0.00183

Measured yesterday against content hash f27933e14523, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wayfinder 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 yesterday.

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.

skills/workflow/wayfinder/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wayfinder

Wayfinder turns a vague, multi-session task into a plan organized around the destination — the end state you are navigating toward — rather than a flat list of steps. It exists for work that cannot be scoped and finished inside a single session: large migrations, cross-cutting features, or ambiguous initiatives where the first hour is spent figuring out what "done" even means.

When to Use

  • The task is too large, ambiguous, or long-running to complete in one session
  • You need a shared map that multiple sessions, agents, or people can navigate from
  • Early exploration keeps surfacing tangents that are real but not part of this pass
  • You need a plan that survives a context reset without losing track of what was deliberately skipped

When NOT to Use

Instead of wayfinder Use
A plan, spec, or PRD already exists and just needs to become tickets to-issues
The work fits in Plan Mode's single-pass plan.md and one session plan-mode-mastery
You need multi-source evidence gathering before deciding anything deep-research
The task is already small enough to execute directly do the task

Wayfinder produces the destination-centric map; to-issues slices an approved plan into dependency-aware tickets; deep-research gathers evidence to inform a decision. Chain them in that order when a large initiative needs all three.

Workflow

1. Name the destination

Write the end state in outcome language, not task language:

Destination: [what the world looks like when this is done]
Not the destination: [adjacent goals this pass explicitly does not include]

A destination is a state, not a checklist. "Auth is fully migrated to the new session store" is a destination. "Update 12 files" is not.

2. Breadth-first triage

Before going deep on any single area, sweep the whole territory once:

  1. List every area that plausibly touches the destination
  2. For each area, spend just enough time to classify it — do not solve anything yet
  3. Sort each area into one of three buckets:
    • In scope — required to reach the destination this pass
    • Fog — unknown enough that it needs its own investigation before it can be scoped
    • Deferred / out of scope — real, but explicitly not part of this destination

Read the full file on GitHub · 194 lines

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. yesterday First seen · 194 lines · 47 tokens per session scan A f27933e14523

Subscribe to this mod's changes

wayfinder is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 8d ago), licensed MIT. It adds 47 tokens to every session and 1,825 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

speckit-workflow

Manage and run Spec Kit automation workflows via specify workflow. USE FOR: running a workflow by ID or local YAML, resuming a paused/failed run, checking run status, listing/installing/removing workflows, searching the workflow catalog, showing a workflow step graph. DO NOT USE FOR: extensions (use…

github/spec-kit-copilot · 93 tokens

declare

Analyzes task plan and declares files that will be created or modified, producing declared-files.json.

rickywo/Formic · 21 tokens

execute

Executes the implementation plan for a Formic task.

rickywo/Formic · 13 tokens

launch-command

Launch orchestration and readiness assessment engine with cross-functional workstream tracking and go/no-go gates. Use when: launch readiness, launch checklist, launch orchestration, go no go, launch plan, are we ready to launch.

varunk130/ai-gtm-skill-library · 48 tokens

decompose

Decompose a feature spec into work items for orchestration via nw. Takes a PRD, phase doc, or verbal description and breaks it into human-reviewable PR-sized work items with dependencies mapped into batches. Use when asked to "decompose", "break down this feature", "create work items for", or "plan the work items".

ninthwave-io/ninthwave · 75 tokens

friction-triage

Interactively walk through every friction log in .ninthwave/friction/ one at a time. For each log: read it, assess severity and possible duplicates, ask the human what to do (fix now / create work item / update doc / drop / merge / skip), execute the decision, and delete the log. This is the canonical way to clear the…

ninthwave-io/ninthwave · 123 tokens