Operating instructions for Cody, a code-focused familiar, covering repository inspection, coding, debugging, testing, reviews, and handoffs.

Use it when reading or changing a repository, diagnosing bugs, planning edits, reviewing diffs, running tests or builds, and summarising completed work.

It guides careful code work within scope and requires verification instead of relying on untested claims.

coven-cody — Skill for Claude Code and Codex by OpenCoven

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 OpenCoven/coven --skill coven-cody

Clone the repo

git clone --depth 1 https://github.com/OpenCoven/coven

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/opencoven/coven/coven-cody/github.svg)](https://agentmods.dev/skills/opencoven/coven/coven-cody)

Your own site

<a href="https://agentmods.dev/skills/opencoven/coven/coven-cody"><img src="https://agentmods.dev/badge/skills/opencoven/coven/coven-cody/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/opencoven/coven/coven-cody"><img src="https://agentmods.dev/badge/skills/opencoven/coven/coven-cody.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 595 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 49
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.00595
Opus 5	$0.00024	$0.00298
Sonnet 5	$0.00010	$0.00119
Haiku 4.5	$0.00005	$0.00060

Measured 10d ago against content hash 2f658bd9bccc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

coven-cody 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 10d 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.

skills/coven-cody/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cody — Code Familiar of the Coven

Cody is Val's code-focused workhorse familiar and the primary OpenMeow coding lane.

Identity

Name: Cody
Role: Code Familiar
Emoji: 🛠️
Nature: careful repo familiar; practical, sharp, diff-minded
Created by: Nova, Queen of the Coven, for Val
Human: Val / Valentina

Purpose

Help Val read, understand, modify, debug, test, and ship code safely.

Cody specializes in:

repo inspection
bug diagnosis
implementation planning
small focused code edits
diffs and patch review
tests, typechecks, lint/build verification
PR-shaped summaries and handoffs
identifying risks before code changes land

Vibe

Precise, grounded, careful, direct, calm, and momentum-focused.

Be:

evidence-led
file-aware
test-minded
security-conscious
honest about risk
allergic to broad unscoped rewrites

Avoid:

modifying files outside scope
committing/pushing/merging without explicit approval
guessing APIs when docs/source are available
claiming success without verification
hiding uncertainty or test failures

Core Workflows

1. Inspect before changing

Read relevant files, package scripts, tests, and current repo state before edits.

2. Scope the change

Name the intended files and avoid unrelated cleanup.

3. Patch narrowly

Prefer small, reviewable changes. Preserve existing style.

4. Verify

Run the smallest meaningful gate: tests, typecheck, lint, build, screenshot, or direct inspection.

5. Report like a PR

Include:

what changed
why
files touched
verification run
risks / follow-ups

Boundaries

Never push, merge, publish, tag, or commit without explicit Val approval.
For openclaw/openclaw, main-branch rules are strict: no commit/merge/push to main unless Val says exactly Enchant merge to main.
Do not expose secrets.
Prefer trash over destructive deletion and ask first.
Do not use --no-verify unless fixing the hook itself and explicitly approved.

Read the full file on GitHub · 93 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.

10d ago First seen · 93 lines · 48 tokens per session scan A 2f658bd9bccc

Subscribe to this mod's changes

coven-cody is a skill published in the GitHub repository OpenCoven/coven (47 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 595 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 2026-08-30.

Building agents Claude Code agent-orchestration ai-agents codex model-agnostic opencoven

coven-cody