init-config

A setup tool that creates a crew.config.yaml file at a repository's root, using the project's detected tools and documentation locations.

In plain words
What is it for?
It is used when setting up or configuring crew so the project gets appropriate install, lint, type-check, test, label, and documentation settings.
Why use it?
It makes the crew workflow's commands, labels, safeguards, and documentation settings explicit while avoiding replacement of an existing configuration file.

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

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 923 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 $0.00062 $0.00923
Opus 5 $0.00031 $0.00462
Sonnet 5 $0.00012 $0.00185
Haiku 4.5 $0.00006 $0.00092

Measured 2d ago against content hash 045d62bfbc19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-config 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.

plugins/crew/skills/init-config/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

init-config

You write a crew.config.yaml at the repo root so crew is tuned to this project. Config is optional — crew works without it — but a config makes label names, guardrails, and commands explicit.

1. Don't clobber

If crew.config.yaml already exists at the repo root, do not overwrite it. Show the user the current contents and offer to adjust specific fields instead.

2. Detect the stack

Run the resolver to see what crew would auto-detect (commands, docs index):

python3 "${CLAUDE_PLUGIN_ROOT}/lib/load_config.py"

Also glance at the repo: package manager / build files, where docs live, and whether the project uses non-default GitHub label names (gh label list).

3. Write the config

Start from the annotated template and fill in what you detected:

cp "${CLAUDE_PLUGIN_ROOT}/templates/crew.config.example.yaml" crew.config.yaml

Then edit crew.config.yaml to reflect this repo:

  • project.name and project.docs_index (real values, or remove docs_index to let crew auto-detect).
  • commands.{install,lint,typecheck,test} — the project's real commands (drop keys the project doesn't have rather than leaving wrong values).
  • labels.* — only if the repo uses non-default label names.
  • guardrails.protected_paths — add this repo's sensitive areas (DB schema migrations, infra, secrets, generated code). The default ships **/migrations/**, but DB migrations are named differently across tools — detect this repo's actual mechanism and add the matching glob: e.g. Liquibase uses **/changelog/** or **/db/changelog/** (and *.changelog.* / changesets), Flyway **/db/migration/**, Rails/Django/Alembic **/migrations/**, golang-migrate **/migrate/**. Match the directory the repo actually uses; don't add a bare **/changelog/** that would also catch a docs CHANGELOG.md. If unsure, glob to the real path you find.
  • mode — leave auto unless the team wants to pin github or local.
  • local.isolation — leave auto (jj if installed, else kosho, else native git worktree); pin it only if the team standardizes on one. Note that jj/auto will colocate jj at the repo root (.jj/ beside .git/) on first local-mode run if it isn't already.
  • Leave orchestrator, team, knowledge, ledger at defaults unless the user wants otherwise.

Read the full file on GitHub · 74 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. 2d ago First seen · 74 lines · 62 tokens per session scan A 045d62bfbc19

Subscribe to this mod's changes

init-config is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 15d ago), licensed MIT. It adds 62 tokens to every session and 923 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

ghost-decode

Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.

haroontrailblazer/ghost-font-decoder · 64 tokens

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.

SethGammon/Citadel · 56 tokens

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens