A guided tool for writing formal specifications—machine-checkable statements about required behavior—for externally reachable functions in a Sui Move smart-contract package.

Use it after adding public or entry functions, to define their conditions and outcomes, run the Sui prover, and produce an HTML audit report.

It helps turn intended behavior into checked guarantees and records progress and results while specifications are written and verified.

specify — Command by contract-hero

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/contract-hero/sui-pilot/specify

Clone the repo

git clone --depth 1 https://github.com/contract-hero/sui-pilot

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 621 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.

Model	Per session	Once invoked
Fable 5	$0.00034	$0.00621
Opus 5	$0.00017	$0.00311
Sonnet 5	$0.00007	$0.00124
Haiku 4.5	$0.00003	$0.00062

Measured 2d ago against content hash e23ac44d5e99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specify 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/specify.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invoke the specify skill to walk through formal-specification authoring for the Move package in the current directory.

What This Command Does

Probes the local sui-prover binary and the package's Move.toml for setup issues (capabilities, edition, implicit-dep readiness).
Discovers every externally reachable function (public non-package + entry) under sources/.
Builds a per-function context (signature, callees, observable effects, abort paths).
Asks the user — one structured AskUserQuestion batch per function — for invariants, preconditions, postconditions, and abort conditions.
Drafts a #[spec(prove)] twin function and writes it inline at the bottom of the same .move file (between // === sui-pilot specify: generated specs === markers).
Runs sui-prover via the sui-prover-mcp MCP and iterates on failures using the failure taxonomy at skills/specify/references/failure-taxonomy.md.
Persists progress to .specify-progress.json at the package root so the flow is resumable.
Emits a self-contained HTML audit at .specify-report.html on completion.

When to Use

After implementing new public / entry functions and before deploying to mainnet.
When introducing formal verification to an existing Move package for the first time.
Pre-audit pass to surface abort conditions and missing invariants.

When NOT to Use

For verifying public(package) or private functions — the prover treats them interchangeably with public, but the specify flow scopes to externally-reachable functions per the plan.
When sui-prover is not installed — install via brew install asymptotic-code/sui-prover/sui-prover first.
When Move.toml still pins Sui or MoveStdlib explicitly — the prover requires Sui 1.45+ implicit-dep injection; the skill will surface a setup_warning and stop.

Limitations

Single-package scope. Cross-package spec generation (the target = other_pkg::mod::fn form) is deferred.
Spec quality is bounded by the user's answers to the AskUserQuestion batches; vague answers produce weak specs.
Some Move code patterns require no_opaque or boogie_opt tuning that the skill suggests but cannot always derive automatically — the failure-taxonomy file documents the manual escape hatches.

Read the full file on GitHub · 42 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.

2d ago First seen · 42 lines · 34 tokens per session scan A e23ac44d5e99

Subscribe to this mod's changes

specify is a command published in the GitHub repository contract-hero/sui-pilot (10 stars, last pushed 8d ago), licensed MIT. It adds 34 tokens to every session and 621 once invoked, about $0.0002 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.

Web3 and blockchain

specify

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

What This Command Does

When to Use

When NOT to Use

Limitations

What this file has done since we first saw it

Other commands, from other repositories

brainblast-firewall

audit-strict

fix-btc-e2e-p6

deploy-testnet

maxia-stocks

setup-ci-cd