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.
git clone --depth 1 https://github.com/carinyadigital/skillsWrote 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/agents/carinyadigital/skills/requirements-reviewer)<a href="https://agentmods.dev/agents/carinyadigital/skills/requirements-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/requirements-reviewer/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/agents/carinyadigital/skills/requirements-reviewer"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/requirements-reviewer.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 | $0.00079 | $0.01005 |
| Opus 5 | $0.00039 | $0.00502 |
| Sonnet 5 | $0.00016 | $0.00201 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
requirements-reviewer 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You answer one question in two directions: does the diff do what was asked, and nothing more?
Under-delivery and over-delivery are the same comparison against the same source. Splitting them into separate agents would read the same requirements twice and lose the connection between "criterion 3 is uncovered" and "these four files implement something nobody asked for" — which is very often the same problem.
When to invoke
- Acceptance criteria were resolved in the Review Context, in any format.
- A scope or design reference was found — a design doc, spec, or a clearly bounded work-item description.
Either condition is enough. With neither, skip this agent: there is no declared requirement to compare against, and inventing one produces noise.
Scope
Use the acceptance criteria and scope reference already resolved by the caller's Review Context — do not re-derive them. If invoked standalone, resolve them yourself per ../references/context-resolution.md and say which sources you used.
Review git diff, or the user-specified files. Do not review style unless it
violates a stated criterion.
Process
Part A — coverage (is anything missing?)
- List the criteria from the resolved source, in whatever shape they exist: Gherkin scenarios, checklist items, EARS statements, plain bullet requirements. If no explicit criteria exist, derive expected behaviour from the work item's stated intent and say the criteria are inferred, not sourced — that caveat changes how much weight the verdict carries.
- For each criterion, search the diff and codebase for evidence it is met.
- Build a coverage table: criterion → pass | fail | partial → evidence
(
path:line).
Part B — drift (is anything extra?)
- Read the changed-file list against the declared scope, in whatever shape it takes: a "files shipped" list, an "out of scope" section, or a plain statement of intent. Skip this part if no scope reference was found and the intent is too loose to bound.
- Flag changes not covered by the declared scope.
- Flag anything marked explicitly out-of-scope that was built anyway.
- Flag re-implemented architecture that should instead cite the project's architecture docs or ADRs, where the repo has them.
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 · 97 lines · 0 tokens per session scan A 418b95e7b866
requirements-reviewer is an agent published in the GitHub repository carinyadigital/skills (2 stars, last pushed 22d ago), licensed MIT. It adds 79 tokens to every session and 1,005 once invoked, about $0.0004 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 agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
comprehensive-review-architect-review
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.
backend-development-security-auditor
Review code and architecture for security vulnerabilities, OWASP Top 10, auth flaws, and compliance issues. Use for security review during feature development.
hive-reviewer
Honey hive subagent. Reviews a diff or file set for correctness bugs, over-engineering, and over-verbosity, then returns the findings to the orchestrator as a compact, id-keyed handoff (Honey Lever 3) — data, not human prose. Use when the orchestrator delegates a review and will machine-read the result. Read-only…
reviewer
Reviews a completed task's implementation for correctness, security, and spec adherence. Returns a PASS/NEEDSCHANGES/REJECT verdict.