contract

A specification-drafting tool that studies examples such as API calls, tests, or input and output pairs to infer the rules behind them.

In plain words
What is it for?
Use it to compare independent interpretations of examples and produce a draft specification with confidence notes.
Why use it?
It helps when the required behavior is shown through examples but has not yet been written down as a clear specification.

Skill for Claude CodeCodex

Part of the agent-workflows plugin — 28 skills, 4 agents, 4 hooks shipped together

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/sjarmak/agent-workflows/contract
Any agent
npx skills add sjarmak/agent-workflows --skill contract
Clone the repo
git clone --depth 1 https://github.com/sjarmak/agent-workflows

Made for: Claude Code, Codex.

Or install agent-workflows, the plugin that ships this one along with the rest of its 28 skills, 4 agents, 4 hooks.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,237 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 $0.00000 $0.02237
Opus 5 $0.00000 $0.01118
Sonnet 5 $0.00000 $0.00447
Haiku 4.5 $0.00000 $0.00224

Measured 2d ago against content hash 40cd6890048e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contract 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.

skills/contract/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specification Generation from Examples. Takes a set of examples (API calls, test cases, user stories, input/output pairs) and spawns N agents to independently INFER the specification that would produce those examples. Each agent works bottom-up: what rules, constraints, invariants, and edge cases does this behavior imply? Agents don't see each other's inferences. Synthesize by comparing: where agents infer the same rule, it's likely correct; where they diverge, the examples are ambiguous or underconstrained. Output is a draft specification with confidence annotations.

Arguments

$ARGUMENTS — format: [N] [path/to/examples or inline examples] where N is optional agent count (default: 3, min 2, max 5)

Parse Arguments

Extract:

  • agent_count: the optional leading integer (default 3, min 2, max 5)
  • input: a file path containing examples, or inline examples provided directly in the argument

If the input is a file path (contains / or ends in a common extension), read the file. Otherwise, treat the entire remaining argument as inline examples.

If no input is provided, ask the user to provide examples before proceeding.

Phase 1: Ingest and Classify Examples

  1. Read the file or parse inline examples
  2. Classify each example into one or more categories:
    • API calls -- request/response pairs, endpoint definitions
    • Test cases -- assertions, expected behaviors, setup/teardown
    • Input/output pairs -- transformation examples, function mappings
    • User stories -- behavioral descriptions, acceptance criteria
    • State transitions -- before/after snapshots, event sequences
    • Error cases -- invalid inputs, expected failures, boundary violations
    • Mixed -- examples that span multiple categories
  3. Count and summarize the example set:
    • Total number of examples
    • Breakdown by category
    • Apparent domain or system being specified
    • Observable patterns (e.g., "all examples involve user authentication", "inputs are always JSON objects")
  4. Present the classification summary to the user and confirm before proceeding. Adjust if the user gives feedback.

Read the full file on GitHub · 207 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 · 207 lines · 0 tokens per session scan A 40cd6890048e

Subscribe to this mod's changes

contract is a skill published in the GitHub repository sjarmak/agent-workflows (9 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,237 tokens. 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

speckit.specify

Skill "speckit.specify" from caipe-io/ai-platform-engineering, covering user input, outline, quick guidelines, section requirements and for ai generation.

caipe-io/ai-platform-engineering · 0 tokens

speckit.clarify

Skill "speckit.clarify" from caipe-io/ai-platform-engineering, covering user input and outline.

caipe-io/ai-platform-engineering · 0 tokens

local-integration-testing

Run end-to-end integration tests with all 15 agents and supervisor in local Docker Compose dev environment. Validates agent discovery, multi-agent routing, checkpoint persistence, and cross-agent follow-up conversations.

caipe-io/ai-platform-engineering · 44 tokens

release-docs

Generate a combined release blog post for ai-platform-engineering. Produces a single docs/releases/YYYY-MM-DD-release-X-Y-Z.md file containing release notes and the upgrade guide (migration guide) inline. Use when cutting a release, when a user asks "what changed in 0.4.x", or when upgrading their values.yaml to a new…

caipe-io/ai-platform-engineering · 76 tokens

update-docs

Audit and update all documentation moving parts for ai-platform-engineering. Checks release blog posts, features page, agent docs, homepage version strings, Docusaurus version config, and sidebar completeness. Fixes what is stale and reports what needs manual attention. Use after cutting a release, adding a new agent…

caipe-io/ai-platform-engineering · 70 tokens

docker-compose-first-install

Validate and repair the OSS first-install Docker Compose path. Use when editing docker-compose.yaml, docker-compose.dev.yaml, .env.example, release image tags, Compose profiles, Keycloak/OpenFGA/RAG defaults, or first-launch UI behavior for local all-in-one installs.

caipe-io/ai-platform-engineering · 60 tokens