Borrowing it
Nothing to install: this file belongs to vinilana/invokta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vinilana/invokta/main/.agents/skills/invokta-contract-review/SKILL.mdgit clone --depth 1 https://github.com/vinilana/invoktaWrote 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/vinilana/invokta/invokta-contract-review)<a href="https://agentmods.dev/skills/vinilana/invokta/invokta-contract-review"><img src="https://agentmods.dev/badge/skills/vinilana/invokta/invokta-contract-review/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/vinilana/invokta/invokta-contract-review"><img src="https://agentmods.dev/badge/skills/vinilana/invokta/invokta-contract-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.00677 |
| Opus 5 | $0.00030 | $0.00338 |
| Sonnet 5 | $0.00012 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
invokta-contract-review 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 11d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invokta Contract Review
Establish the source of truth
- Read
docs/README.mdanddocs/vision-and-invariants.md. - Compare the change with
docs/architecture.md,docs/scope-and-limits.md,docs/implementation-plan-and-acceptance-criteria.md,docs/adr/README.md, and applicable ADRs. - Inspect public types, acceptance tests, and the existing implementation. Do not infer guarantees from examples or internal details.
- Identify the consumer, public surface, and change type: additive, compatible, ambiguous, or breaking.
- Stay read-only for review requests. Edit only when the user requests fixes.
Apply the gates
Gate 1 — Complete surface
Inventory each applicable concern:
- operations, inputs, outputs, and observable effects;
- public errors, codes, stable messages, and retry policy;
- defaults, configuration, ordering, and determinism;
- timeouts, cancellation, concurrency, and idempotency;
- size, count, depth, time, and resource limits;
- versioning, migration, and backward compatibility;
- responsible ports and ADR-authorized adapters.
Mark missing details as unspecified; do not fill gaps with assumptions.
Gate 2 — Executable acceptance
- Rewrite vague requirements as binary, observable outcomes.
- Map
requirement → contract → acceptance test → evidence. - Require happy paths, expected errors, and inclusive and exclusive boundary cases.
- Reject criteria based only on internal structure, subjective adjectives, or undefined future implementation.
Gate 3 — Limits and failures
- Verify validation at the correct boundary and consistent behavior across adapters.
- Require safe, deterministic failure for invalid input, limit violations, unavailability, and cancellation.
- Find unbounded resources, duplicate work, uncontrolled growth, and external dependencies without timeouts.
- Confirm that logs, metrics, and errors expose no secrets or sensitive content.
Gate 4 — Architecture and evolution
- Confirm dependency direction and each port and adapter responsibility against the ADRs.
- Flag framework, transport, or persistence types that leak into the domain.
- Separate intentional contracts from implementation details. Prevent public tests from freezing internal details.
- Classify compatibility breaks and require an explicit decision, version, or migration.
What ships with it
1 file 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.
- 11d ago First seen · 68 lines · 59 tokens per session scan A df7b668349a3
invokta-contract-review is a skill published in the GitHub repository vinilana/invokta (129 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 677 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 2026-08-30.
Other skills, from other repositories
platform-apex-generate
Primary Apex authoring skill for class generation, refactoring, and review. ALWAYS ACTIVATE when the user mentions Apex, .cls, triggers, or asks to create/refactor a class (service, selector, domain, batch, queueable, schedulable, invocable, DTO, utility, interface, abstract, exception, REST resource). Use this skill…
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
api-contract-review
Use when auditing CloudBase cloud API wrappers, MCP tools, generated action metadata, or related docs for outdated or incorrect action names, parameters, casing, request shapes, or missing contract tests, especially during periodic quality review or before preparing corrective PRs.
principle-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
api-reviewer
A review of an API contract, the agreed description of how software systems exchange requests, responses, events, or files.