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.
npx agentmods add skills/contract-hero/sui-pilot/specifynpx skills add contract-hero/sui-pilot --skill specifygit clone --depth 1 https://github.com/contract-hero/sui-pilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/contract-hero/sui-pilot/specify)<a href="https://agentmods.dev/skills/contract-hero/sui-pilot/specify"><img src="https://agentmods.dev/badge/skills/contract-hero/sui-pilot/specify.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00174 | $0.09559 |
| Opus 5 | $0.00087 | $0.04779 |
| Sonnet 5 | $0.00035 | $0.01912 |
| Haiku 4.5 | $0.00017 | $0.00956 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specify — formal specifications for Sui Move
Doc-First Requirement. Read
.sui-prover-docs/before drafting any spec. The Sui Prover spec language is not the legacy Move Prover MSL — it uses#[spec(prove)],requires,ensures,asserts(positive abort form), and the macrosclone!,forall!,exists!,invariant!. It does NOT useaborts_if,pragma,apply,assume, or freeaxiom. Verify any construct against.sui-prover-docs/guide/spec-reference.mdbefore emitting it.
Deliverable shape (read first)
/specify ships three artifacts, not one. This is the load-bearing architectural decision (docs/specify-deliverable-design.html, learning L1, validated against ~/workspace/integer-library):
- The production package — left pristine. No
#[spec_only], no prover dependency, no marker blocks. Verification scaffolding never touches deployed source. - One or more spec packages. A sibling
<pkg>_specs/package holds#[spec(prove, target = <pkg>::<mod>::<fn>)]twins, one<mod>_specs.moveper source module. A function that needs a custom prover invocation (e.g.--no-bv-int-encodingfor bit-exact semantics) goes in a second package<pkg>_specs_bv/(Phase 4.6). - The report + manifest. A self-contained HTML report (invariant-driven, per Phase 5) plus
spec-context.jsonbinding each spec to its source state, dep pins, toolchain versions, and per-package prover flags.
The legacy inline layout (specs in the production .move between markers) is now opt-in only via --inline, for single-module throwaway packages where a sibling package is overkill. Default is always the separate package.
Non-interactive (eval) mode
This skill is interactive by default — every gate runs through AskUserQuestion. Non-interactive mode activates via either of two triggers:
- Environment-flag trigger. Before doing anything else, run
echo "${SPECIFY_AUTO_DEFAULTS:-}"via Bash. If the output is exactly1, this run is in non-interactive mode (typically becauseevals/run-comparison.shor a similar headless rig is driving it). - Verbal-directive trigger. The user has explicitly said something like "don't stop", "don't pause", "work autonomously", "no questions", "proceed without asking", or "no-pause" in the current conversation. A
Stophook with an autonomy-oriented condition counts as such a directive.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 446 lines · 174 tokens per session scan A 23c8490b1e67
specify is a skill published in the GitHub repository contract-hero/sui-pilot (10 stars, last pushed 3d ago), licensed MIT. It adds 174 tokens to every session and 9,559 once invoked, about $0.0009 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…