contract

A command for managing feature contracts, which are written agreements describing what a change must do. It can pick up requirements from sources such as Jira, documents, Slack, Notion, or Figma, then help fix, split, verify, diagram, promote, migrate, or archive them.

In plain words
What is it for?
Use it to start a feature specification from a link, text, or image, refine its requirements, break large work into parts, visualize it, verify it, or move it through its lifecycle.
Why use it?
It turns scattered requirements into a traceable specification before implementation. This helps clarify expected behavior and supports checking whether the finished work meets the agreement.

Command

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 commands/iampawan/manifest/contract
Clone the repo
git clone --depth 1 https://github.com/iampawan/Manifest
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,582 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 $0.00068 $0.02582
Opus 5 $0.00034 $0.01291
Sonnet 5 $0.00014 $0.00516
Haiku 4.5 $0.00007 $0.00258

Measured 2d ago against content hash 5deea87aaa3b, 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.

commands/contract.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/contract

The umbrella command for contract lifecycle operations.

If you're new — start here

Running /contract with no arguments? You're probably looking for a quick tutorial. Invoke the tutorial skill — it adapts to what you want to learn:

/manifest tutorial      # 3-minute walkthrough
/manifest help          # reference card

Or jump right in:

/contract pickup <a JIRA / Doc / Slack URL, or "a description">

Subcommands

/contract pickup (canonical Spec entry)

The single entry point for getting a feature spec'd. Source is anything:

/contract pickup https://your-org.atlassian.net/browse/ENG-1234
/contract pickup https://docs.google.com/document/d/<...>
/contract pickup https://linear.app/<org>/issue/ENG-987
/contract pickup https://notion.so/<page-id>
/contract pickup https://yourcorp.slack.com/archives/C123/p1234567890
/contract pickup https://figma.com/file/<...>
/contract pickup "Add CSV export to /admin/users"                     # free-text
/contract pickup        # then paste text or drop an image

What it does:

  • Detects the source type and fetches via the right MCP. Follows embedded links one level deep (Figma inside JIRA, tech spec inside the Google Doc).
  • Pulls related history in the background — past contracts on the same surface, postmortems, recent Sentry, open PRs touching the same files.
  • Drafts the contract, runs the validator + the relevant judgment critics in parallel, plus a dev-side critic-code-context that surfaces auto-fill proposals from the repo.
  • Sorts every gap into three buckets: A. agent fills from code (one tap to accept) · B. dev decides (engineering judgment) · C. only PM can answer (drafted as PM-facing questions).
  • For Bucket C, agent composes one batched message in the dev's voice on the channel the source came from — JIRA comment, Slack reply, Notion comment, Google Doc suggestion. PM never has to touch Manifest.
  • Watches the channel for replies; when PM answers, the answer materializes as an AC edit with a provenance comment, the question moves to a <ID>.qa.md sidecar, and the contract re-verifies incrementally.

Read the full file on GitHub · 270 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 · 270 lines · 0 tokens per session scan A 5deea87aaa3b

Subscribe to this mod's changes

contract is a command published in the GitHub repository iampawan/Manifest (5 stars, last pushed 21d ago), licensed MIT. It adds 68 tokens to every session and 2,582 once invoked, about $0.0003 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.