A setup skill for scanning existing, partly documented repositories and configuring defaults for prism analysis tools. A brownfield repository is an established codebase that already contains code and history.

Use it to perform first-time setup, scan repositories, configure runtime defaults, register brownfield codebases, or select which repositories prism should use.

It helps the analysis tools find the relevant repositories and use the correct runtime and configuration before other prism skills are run.

setup — Skill by cohemm

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/cohemm/prism/setup

Any agent

npx skills add cohemm/prism --skill setup

Clone the repo

git clone --depth 1 https://github.com/cohemm/prism

Made for: Claude Code, Codex.

Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,419 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.02419
Opus 5	$0.00006	$0.01210
Sonnet 5	$0.00002	$0.00484
Haiku 4.5	$0.00001	$0.00242

Measured yesterday against content hash 6185062749c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup 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/setup/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prism Setup

Configure Prism's runtime backend and register brownfield repositories so prism skills (analyze, incident, prd) can use the correct agent runtime and codebase context during analysis.

Usage

/prism:setup
/prism:setup scan
/prism:setup defaults
/prism:setup set 6,18,19

Use /prism:setup for the full first-run setup flow. The setup subcommands mirror the brownfield management actions while keeping the setup-specific runtime/backend verification.

Note: Prism runtime selection now lives in ~/.prism/config.yaml. Claude Code and Codex can coexist; setup selects the active backend instead of hard-mapping the engine.

How It Works

Default flow (no args)

Step 0: Runtime Configuration

Before brownfield scanning, ensure Prism's runtime config matches the current surface.

If this skill was invoked as psm setup inside Codex:
1. Run: bash ${PRISM_REPO_PATH}/scripts/setup.sh --runtime codex
2. This must install/update the managed Codex MCP hookup, refresh ~/.codex/skills/prism-* and ~/.codex/rules/prism.md from the repo source, and write ~/.prism/config.yaml with runtime.backend: codex.
3. Treat the checked-in repo skills/ directory as the authored source of truth. Any installed ~/.codex/skills/prism-* entries are managed mirrors for Codex discovery only.
If this skill was invoked as /prism:setup inside Claude Code:
1. Run: bash ${PRISM_REPO_PATH}/scripts/setup.sh --runtime claude
2. This must write ~/.prism/config.yaml with runtime.backend: claude.
3. Validate that the checked-in commands/ and skills/ directories still exist in the Prism repo before continuing. Those repo paths are the canonical shared source for Claude.
4. Do not create or sync duplicate Claude slash-command artifacts during this step. Claude should use the checked-in commands/ and skills/ directories from the Prism repo directly.

After the command completes, tell the user which backend is active and where the config lives: Prism runtime configured: <backend> (~/.prism/config.yaml)

Read the full file on GitHub · 254 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.

yesterday First seen · 254 lines · 12 tokens per session scan A 6185062749c7

Subscribe to this mod's changes

setup is a skill published in the GitHub repository cohemm/prism (5 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 2,419 once invoked, about $0.0001 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens