orient

A project-onboarding workflow that studies a repository, installs predicate’s checks, and creates an AGENTS.md file describing the project’s goals and rules. It is intended as the first predicate workflow used on a project.

In plain words
What is it for?
Use it to onboard a repository, map its structure, define its goal, install enforcement, and prepare project guidance for future agent work.
Why use it?
It gives later coding-agent work a shared understanding of the repository and a persistent set of constraints. It also pauses at defined points when human decisions are needed.

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/nrdxp/predicate/orient
Any agent
npx skills add nrdxp/predicate --skill orient
Clone the repo
git clone --depth 1 https://github.com/nrdxp/predicate

Made for: Claude Code, Codex.

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,541 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 $0.00120 $0.03541
Opus 5 $0.00060 $0.01770
Sonnet 5 $0.00024 $0.00708
Haiku 4.5 $0.00012 $0.00354

Measured yesterday against content hash 0b2fa6ef878a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orient 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/orient/SKILL.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orient: Project Orientation Workflow

Predicate is project-centric: /orient is its first contact with a project. It engages this repository concretely — installs predicate's enforcement, maps the repo, learns its goal, and authors the persistent conditioning layer (the AGENTS.md goal-hierarchy) so every subsequent walk is anchored and gated. Not an idealized formula imposed from outside; a boundary fitted to the actual project.

Quickstart: install predicate into your harness → target a project → run /orient.


Phases (state machine; halts at the two human seams)

The eight phases execute in order. Two are human seams — the walk halts and awaits human input before continuing. The others are mechanical or agent-automated.

Phase 0 — BOUND (compose /boundary — do not rush)

Before touching the repo, invoke /boundary to draft an IBC for the orientation work itself: what is this project, what is known vs unknown going in, what is the desired end state of onboarding it.

/boundary is also the authority for the AGENTS.md contract the AUTHOR phase (phase 6) conforms to — composed here, not duplicated. The required content (Goal, Requirements/Invariants/Constraints, Unknowns, Operational entrypoint, Structure, Alignment-to-parent) and the soundness invariants are defined in /boundary §AGENTS.md.

Phase 1 — ESTABLISH (mechanical, automated — no human input)

Run bootstrap/install.sh init --project <dir>: install git hooks into .git/hooks (untracked, auditable, removable), initialize the .ledger sub-repository, wire project config. Idempotent — safe to re-run on an already-oriented project.

Phase 2 — MAP (domain — outward→structure; cheapest tier; hunt-to-dry)

Fan out a multi-modal sweep over the repository:

  • Structuregit ls-files for the file tree; directory layout.
  • Semantics — what each component does; package/module roles.
  • Historygit log shape; maturity signals; areas of churn.
  • Docs — stated purpose in READMEs, existing AGENTS.md files, or architectural docs.

Read the full file on GitHub · 326 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 326 lines · 120 tokens per session scan A 0b2fa6ef878a

Subscribe to this mod's changes

orient is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 8d ago), licensed MIT. It adds 120 tokens to every session and 3,541 once invoked, about $0.0006 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

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