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 skills add pekral/cursor-rules --skill assignment-compliance-checkgit clone --depth 1 https://github.com/pekral/cursor-rulesWrote 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/pekral/cursor-rules/assignment-compliance-check)<a href="https://agentmods.dev/skills/pekral/cursor-rules/assignment-compliance-check"><img src="https://agentmods.dev/badge/skills/pekral/cursor-rules/assignment-compliance-check/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/pekral/cursor-rules/assignment-compliance-check"><img src="https://agentmods.dev/badge/skills/pekral/cursor-rules/assignment-compliance-check.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 | $0.00135 | $0.03081 |
| Opus 5.5 | $0.00054 | $0.01232 |
| Sonnet 5.5 | $0.00027 | $0.00616 |
| Haiku 4.5 | $0.00014 | $0.00308 |
Grade A, and why
assignment-compliance-check 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constraints
- Apply
@rules/php/core-standards.mdc - Apply
@rules/git/general.mdc - Apply
@rules/jira/general.mdc - Apply
@rules/reports/general.mdc— the Assignment Compliance markdown block this skill returns to the caller must be written in the language of the linked assignment (Czech issue / JIRA description → Czech block; English → English). Linked-task / PR URLs, author handles, and severity labels follow the rule's Scope clarifications. - The skill must not write any output to disk. It also must not publish anywhere itself — no
gh issue comment, noacli, no JIRA / GitHub MCP write call. The skill returns either the assembled markdown block (on every run that has a linked tracker, including the affirmative report on a clean run) or a skip status (only when no linked tracker is detected) to the calling CR wrapper. The wrapper embeds the block into the single consolidated linked-tracker comment authored by@skills/pr-summary/SKILL.md(one comment per linked issue / JIRA ticket per CR run — see issue #498) only when a block is returned; on the skip status the wrapper embeds nothing and surfaces the status only on the PR comment summary line. - The block must not be embedded into the GitHub PR comment produced by
@skills/code-review/SKILL.md,@skills/code-review-github/SKILL.md, or@skills/code-review-jira/SKILL.md. The PR comment carries technical findings; the linked-tracker comment carries assignment compliance as part of the consolidatedpr-summaryoutput. - The published block must be plain language understandable by a non-technical reader. Include a short example for every criterion that is Not met / Partial / Divergent, and a one-line citation of the requirement for every Met criterion. Do not list open questions for the reviewer — those are out of scope for this skill; only acceptance-criteria status belongs here.
- The published comment must credit the real change author(s) in the
Authorsline — resolved exactly as@skills/pr-summary/SKILL.mdresolves them (git history%an <%ae>+ PRauthor.login+commits[].author.login, JIRA display name when the target is JIRA). Never list the agent / CR identity. When authorship cannot be determined, writeunknown — git history did not yield a recognisable identity. - The published comment must include the
Available behindline whenever the change is reachable only behind a test parameter (feature flag, ENV switch, query-string parameter, request header, A/B variant, admin toggle, allow-listed account). Detect the gating toggle the same way@skills/pr-summary/SKILL.mddoes (scan the diff forconfig('…')/env('…')checks, GrowthBook / Unleash / LaunchDarkly calls, query / header gates, allow-list middleware), name the toggle, and state the value required to reach the change. Omit the line entirely only when the change is reachable unconditionally. - Report every extracted acceptance criterion — Met and unmet alike — scoped to functional / business-logic conformance only. Do not report architecture, code style, test coverage, refactoring opportunities, or any other concern — those are owned by the other review skills.
- Never modify code. This skill is read-only with respect to the codebase.
- Do not expose secrets, internal infrastructure paths, or PII in the comment.
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 · 107 lines · 135 tokens per session scan A 47b1e45d7fd5
assignment-compliance-check is a skill published in the GitHub repository pekral/cursor-rules (11 stars, last pushed 19d ago), licensed MIT. It adds 135 tokens to every session and 3,081 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Test Scaffold (Laravel/PHPUnit)
Generate PHP/Laravel (PHPUnit) test skeletons from specifications.
Laravel Eloquent N+1 and Query Efficiency Review
Detects N+1 query patterns (relation access inside loops without eager loading), full-table get()/all() loads, and unsafe chunk()/cursor() usage in Laravel Eloquent code.
Laravel Mass Assignment and Authorization Review
Detects mass assignment via create/update($request->all()), unguarded models, and missing authorization on mutating controller actions in Laravel.
Laravel Migration Safety Review
Reviews Laravel migrations for destructive operations, change() dropping modifiers, locking index creation on large tables (PostgreSQL), and asymmetric down().
knossos
Use when you need to know what depends on something, what a change would break, where a new file belongs, how a request reaches a given component, or who calls a function, in a repository that Knossos has scanned. Answers come from a static graph with file and line evidence instead of from reading the source tree.…
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.