contract

A command for designing a software interface before building it. It defines expected inputs, outputs, and errors, then checks those rules with tests before implementation.

In plain words
What is it for?
Use it to plan modules, get approval for their interfaces, write tests that initially fail, and implement until those tests pass.
Why use it?
It reduces the risk of building the wrong interface or changing its agreed behaviour during implementation. Contract tests are tests for the interface’s promises, not its internal code.

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/fockus/skill-memory-bank/contract
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 355 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 $0.00014 $0.00355
Opus 5 $0.00007 $0.00178
Sonnet 5 $0.00003 $0.00071
Haiku 4.5 $0.00001 $0.00036

Measured 2d ago against content hash ce87484d16fb, 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 · 47 lines

What it actually says

Contract-First: $ARGUMENTS

0. Validate arguments

If $ARGUMENTS is empty, stop and ask the user for the module / interface name to design. Do not proceed with an empty target.

1. Analysis

  • Study the existing interfaces and contracts in the project
  • Read ./.memory-bank/roadmap.md and any ADRs if they exist
  • Determine which layers are affected (handler / service / repository / infra)

2. Define the contract

Show me first:

  • The interface (method signatures, input/output types)
  • Usage examples (Specification by Example): concrete inputs → expected outputs
  • Failure scenarios: what can go wrong → which errors are returned

Ask for confirmation before continuing.

3. Contract tests

After the contract is approved:

  • Write tests for the interface (Testing Trophy: prioritize integration tests)
  • Tests must verify the contract, not the implementation
  • Tests should fail first (the implementation does not exist yet)
  • Run them and make sure they fail for the right reason

4. Implementation

  • Implement the interface
  • Run the contract tests — all must pass
  • Contract tests must NOT change during implementation. If you need to change them, the contract was defined incorrectly; go back to step 2

5. Finalization

  • Run the full test suite
  • If Memory Bank is active, add a note in notes/
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 · 47 lines · 14 tokens per session scan A ce87484d16fb

Subscribe to this mod's changes

contract is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 355 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 2026-08-30.