Codex

forme-manifest

Read a multi-service OpenProse program directory, analyze all service contracts, and generate the Forme wiring manifest for inspection and debugging

104 stars

Best use case

forme-manifest is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

It is a strong fit for teams already working in Codex.

Read a multi-service OpenProse program directory, analyze all service contracts, and generate the Forme wiring manifest for inspection and debugging

Teams using forme-manifest should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/forme-manifest/SKILL.md --create-dirs "https://raw.githubusercontent.com/jmagly/aiwg/main/.agents/skills/forme-manifest/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/forme-manifest/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How forme-manifest Compares

Feature / Agentforme-manifestStandard Approach
Platform SupportCodexLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Read a multi-service OpenProse program directory, analyze all service contracts, and generate the Forme wiring manifest for inspection and debugging

Which AI agents support this skill?

This skill is designed for Codex.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Forme Manifest Skill

You analyze a multi-service OpenProse program directory by reading all service contracts and generating the wiring manifest that the Forme Container would produce — without executing the program.

## Triggers

- "show forme manifest" / "generate wiring manifest"
- "how does this prose program wire together"
- "forme manifest [path]"
- "show dependency graph for [program]"
- "what's the wiring for [program]"

## Input

A path to a directory containing a multi-service OpenProse program (must have an `index.md` with `kind: program` and a `services:` list).

## Behavior

### Step 0: Detect OpenProse Installation

Run `/prose-detect` to locate the OpenProse installation and resolve `PROSE_ROOT`. The Forme Container spec at `$PROSE_ROOT/forme.md` drives the wiring semantics used in this analysis. If not found, stop and report:

```
OpenProse not found. Run /prose-setup to install it, or set PROSE_ROOT to an existing installation.
```

### Step 1: Read Entry Point

Read `index.md` (or the specified entry file) in the directory. Extract:
- Program name
- Services list
- Program-level `requires:` (external inputs)
- Program-level `ensures:` (final outputs)

### Step 2: Read All Service Contracts

For each service in the `services:` list:
1. Read `{service-name}.md` from the same directory
2. Extract `requires:` (what this service needs)
3. Extract `ensures:` (what this service produces)
4. Extract `strategies:` (conditional behavior)

### Step 3: Build Dependency Graph

Match outputs to inputs by semantic understanding:

For each service's `requires:` entry:
1. Check if it matches the program's `requires:` (external input)
2. Check if it matches another service's `ensures:` (internal wiring)
3. If no match found: flag as **unwired dependency**

For each service's `ensures:` entry:
1. Check if it's consumed by another service's `requires:`
2. Check if it maps to the program's `ensures:` (final output)
3. If not consumed: flag as **unused output** (warning)

### Step 4: Determine Execution Order

Build a topological sort of the dependency graph:
- Services with only external inputs execute first
- Services depending on other services' outputs execute after their dependencies
- Services with no dependencies between them can execute in parallel

### Step 5: Output Manifest

```markdown
## Forme Wiring Manifest

**Program**: {name}
**Services**: {count}
**External Inputs**: {count}
**Final Outputs**: {count}

### Service Contracts

| Service | Requires | Ensures |
|---------|----------|---------|
| {name} | {requires list} | {ensures list} |

### Wiring Graph

```
{service_a}.{output} → {service_b}.requires.{input}
{service_b}.{output} → {service_c}.requires.{input}
{program}.requires.{input} → {service_a}.requires.{input}
{service_c}.{output} → {program}.ensures.{output}
```

### Execution Order

1. {service_a} (depends on: external inputs only)
2. {service_b} (depends on: {service_a})
3. {service_c} (depends on: {service_b})

**Parallel groups**: [{service_a}] → [{service_b}] → [{service_c}]

### Issues

- {any unwired dependencies}
- {any unused outputs}
- {any circular dependencies}

### Mermaid Diagram

```mermaid
graph LR
    Input[Program Input] --> A[{service_a}]
    A --> B[{service_b}]
    B --> C[{service_c}]
    C --> Output[Program Output]
```
```

## Edge Cases

- **Single-component program**: Report that wiring is not needed — program is self-contained
- **Missing service file**: Report as error with path that was expected
- **Circular dependency**: Report as error — cannot determine execution order
- **Ambiguous wiring**: When multiple services could satisfy a requirement, list all candidates and flag for human decision

## Model

This skill runs on **Sonnet** — contract analysis requires moderate reasoning but not Opus-level complexity.

## References

- @$AIWG_ROOT/agentic/code/addons/prose-integration/README.md — prose-integration addon overview
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/research-before-decision.md — Run prose-detect before operating
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/vague-discretion.md — Report ambiguous wiring explicitly rather than resolving silently
- @$AIWG_ROOT/docs/cli-reference.md — CLI reference for AIWG addon integration commands

Related Skills

contract-manifest

104
from jmagly/aiwg

Generate a human-readable manifest for a chain of AIWG skills, showing agent assignments, contract fields (requires:/ensures:), data flow between steps, and parallelization opportunities. Makes orchestration graphs debuggable and auditable.

Codex

aiwg-orchestrate

104
from jmagly/aiwg

Route structured artifact work to AIWG workflows via MCP with zero parent context cost

venv-manager

104
from jmagly/aiwg

Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.

pytest-runner

104
from jmagly/aiwg

Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.

vitest-runner

104
from jmagly/aiwg

Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.

eslint-checker

104
from jmagly/aiwg

Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.

repo-analyzer

104
from jmagly/aiwg

Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.

pr-reviewer

104
from jmagly/aiwg

Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.

YouTube Acquisition

104
from jmagly/aiwg

yt-dlp patterns for acquiring content from YouTube and video platforms

Quality Filtering

104
from jmagly/aiwg

Accept/reject logic and quality scoring heuristics for media content

Provenance Tracking

104
from jmagly/aiwg

W3C PROV-O patterns for tracking media derivation chains and production history

Metadata Tagging

104
from jmagly/aiwg

opustags and ffmpeg patterns for applying metadata to audio and video files