Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ramboz/jignpx agentmods add skills/ramboz/jig/contractsWrote 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/ramboz/jig/contracts)<a href="https://agentmods.dev/skills/ramboz/jig/contracts"><img src="https://agentmods.dev/badge/skills/ramboz/jig/contracts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ramboz/jig/contracts"><img src="https://agentmods.dev/badge/skills/ramboz/jig/contracts.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00163 | $0.03394 |
| Opus 5.5 | $0.00065 | $0.01358 |
| Sonnet 5.5 | $0.00033 | $0.00679 |
| Haiku 4.5 | $0.00016 | $0.00339 |
Grade A, and why
contracts 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 1mo 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec 022 promoted this skill from a deliberate stub (ADR-0002) to jig's team baseline for external-interface contract artifacts, following the reframing in ADR-0005. Like
/jig:pr-review(spec 012),/jig:arch-review(spec 014), and/jig:vision-elicitation(spec 017), it ships as SKILL.md only — no.pyhelper. The skill recommends the canonical industry-standard schema per external surface and points at the ecosystem tools that validate it. It does not write schemas, not scaffold acontracts/directory, and not enforce contracts via PreToolUse hooks. Enforcement is structural via the spec-author's first-pass attention and the independent-review reviewer prompt's second-pass check — both wired in slice 022-02.
What this skill does
For each external surface a project exposes (HTTP API, event bus, RPC, GraphQL, internal data shapes, CLI output, config), this skill recommends:
- The canonical artifact — what to put on disk (e.g.,
openapi.yaml,*.schema.json,*.proto,schema.graphql). - The validation tool — what runs in CI to keep code and artifact
in sync (e.g.,
spectral lint,ajv validate,buf lint,graphql-inspector diff). - The codegen tool — what produces typed clients / server stubs /
TS types from the artifact, when ecosystem-appropriate (e.g.,
openapi-typescript,quicktype,buf generate).
The skill is breadth over depth: catch the right artifact per surface, leave language-specific niceties (Zod vs JSON Schema vs Pydantic vs TypeBox for internal shapes) to a richer user-installed contracts skill or to the dev's judgment. The recommendations are a nudge; the dev decides whether to follow them.
When to use vs. when to defer
- Any other installed contracts skill. Common location:
~/.claude/skills/contracts/— but the deferral is category-based, not name-based, so a skill named anything (contracts,schema-design,contract-first,api-contracts, etc.) whose description claims external-interface contract artifacts, API schema design, or contract-first workflow will be preferred. If one is present, defer to it. The Claude Code skill router should route to the more specific skill automatically; if you want to be sure, explicitly invoke it. /jig:arch-review— sibling jig skill that reviews the design of an API surface (the proposal, the trade-offs, the failure modes). This skill is downstream: once the design is locked, formalize the resulting interface as a contract artifact. Reach for/jig:arch-reviewto debate whether the API should exist; reach for this skill once it does./jig:adr-workflow— if the dev decides to systematically opt out of the canonical recommendation for a surface (e.g., "we'll keep our bespoke env-contract checker, not migrate to a JSON Schema + ajv triple"), capture the rationale in an ADR. This skill nudges; ADRs document the choice when the nudge is declined.- The deferred ADR-0002 stub concept (internal module-boundary enforcement, cross-module Python imports, kitchen-sink scaffolding). Not this skill. ADR-0002 stays in force for the internal-boundary problem; ADR-0005 carved out external-interface artifacts as the separate concern this skill addresses.
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.
- 1mo ago First seen · 237 lines · 163 tokens per session scan A c6747322cb3f
contracts is a skill published in the GitHub repository ramboz/jig (7 stars, last pushed 3d ago), licensed MIT. It adds 163 tokens to every session and 3,394 once invoked, about $0.0007 per session on Opus 5.5. 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
architecture
Proactive architecture review — explore codebase structure, generate a self-contained HTML report with Mermaid diagrams and candidate improvements, then grill the findings. Use when planning a large refactor, onboarding to an unfamiliar codebase, or before a major architectural change.
onboarding
Skill "onboarding" from knitli/toolshed, covering codeweaver first-run onboarding, your goal, setup flow, 1. welcome & overview and 2. embedding provider selection.
setup
Skill "setup" from knitli/toolshed, covering codeweaver setup / reconfiguration, your goal, setup flow, 1. welcome & context and 2. embedding provider selection.
build-falco-web-app
Build or modify a Falco web application in idiomatic F#, using functional routing, request and response helpers, explicit ASP.NET Core integration, security boundaries, and focused tests.
build-giraffe-web-app
Build or modify a Giraffe web application in idiomatic F#, using composable HttpHandler functions, explicit ASP.NET Core integration, configuration, authentication, and focused endpoint tests.
build-oxpecker-web-app
Build or modify an Oxpecker web application in idiomatic F#, using endpoint routing, functional EndpointHandler and EndpointMiddleware composition, ASP.NET Core metadata, and focused endpoint tests.