init

init is a skill for Claude Code from tjqscott/dory. It costs 46 tokens per session (594 once invoked), scanned B, original, MIT.

A setup skill for adding Dory to a repository. It explores the project, creates a wiki from a template, fills its index, copies existing decisions and findings, and can connect a usage status line.

In plain words
What is it for?
Use it when a repository has no wiki or when asked to set up Dory, including running the wiki-tree validation and asking before changing user settings.
Why use it?
Starting project memory by hand can miss important modules, existing notes, or required checks. This process creates the initial structure without overwriting existing files.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions AGENTS.md.

Part of the dory plugin — 5 skills, 3 hooks shipped together

Good fit Use it when a repository has no wiki or when asked to set up Dory, including running the wiki-tree validation and asking before changing user settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tjqscott/dory/init
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.

Any agent
npx skills add tjqscott/dory --skill init
Clone the repo
git clone --depth 1 https://github.com/tjqscott/dory

Made for: Claude Code.

Or install dory, the plugin that ships this one along with the rest of its 5 skills, 3 hooks.

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 init

README.md
[![agentmods](https://agentmods.dev/badge/skills/tjqscott/dory/init/github.svg)](https://agentmods.dev/skills/tjqscott/dory/init)
Your own site
<a href="https://agentmods.dev/skills/tjqscott/dory/init"><img src="https://agentmods.dev/badge/skills/tjqscott/dory/init/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for init

Your own site · 80×15
<a href="https://agentmods.dev/skills/tjqscott/dory/init"><img src="https://agentmods.dev/badge/skills/tjqscott/dory/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 594 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00046 $0.00594
Opus 5.5 $0.00018 $0.00238
Sonnet 5.5 $0.00009 $0.00119
Haiku 4.5 $0.00005 $0.00059

Measured 17d ago against content hash 15ae6400a702, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

init scanned grade B with 1 finding 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 17d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

5. **Usage statusline.** Ask before changing settings. Hooks can't see rate limits, so the prompt hook's usage numbers come from the statusline. If the user agrees, set `statusLine` in `~/.claude/settings.json` to a comm
code/skills/init/SKILL.md · 19 lines

What it actually says

Set up Dory

Paths are relative to this skill's base directory. Run scripts with Python 3.

  1. Explore before writing. Read the README and any docs. Run a tree of the repo to depth 3, skipping dependency and build folders, and head a few data files. Note anything that already records decisions or findings (a CHANGELOG, docs/, a findings file).
  2. Create wiki/ by copying ../../wiki-template/ into the repo root. Never overwrite a file that exists.
  3. Fill the index. Add a line to wiki/index.md for each real module or subject found in step 1, saying when to open it. Create a page only for something a stranger could not get from the code (AGENTS.md V, What Earns a Page). Copy existing decisions and findings into decisions.md and tried.md, and tell the user which originals are now superseded; don't delete them.
  4. Lint: python ../../scripts/wiki_tree.py wiki --write from the repo root. It must report 0 problems.
  5. Usage statusline. Ask before changing settings. Hooks can't see rate limits, so the prompt hook's usage numbers come from the statusline. If the user agrees, set statusLine in ~/.claude/settings.json to a command running sh <plugin>/code/hooks/py.sh <plugin>/code/scripts/usage_statusline.py, with real absolute paths. If a statusline exists already, show the user what to add to it instead of replacing it.
  6. Obsidian (optional). Offer to link wiki/ into the user's vault so it shows in their graph. On Windows, mklink /J "<vault>\<project>" "<repo>\wiki" works without admin. Elsewhere, ln -s "<repo>/wiki" "<vault>/<project>". Then offer one of the two graph plugins. The user installs it in Obsidian under Settings → Community plugins:
  7. Report what was created and the lint result.
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. 17d ago First seen · 19 lines · 46 tokens per session scan B 15ae6400a702

Subscribe to this mod's changes

init is a skill published in the GitHub repository tjqscott/dory (60 stars, last pushed 11d ago), licensed MIT. It adds 46 tokens to every session and 594 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.