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/reidemeister94/development-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/reidemeister94/development-skills/staff-reviewer)<a href="https://agentmods.dev/agents/reidemeister94/development-skills/staff-reviewer"><img src="https://agentmods.dev/badge/agents/reidemeister94/development-skills/staff-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/reidemeister94/development-skills/staff-reviewer"><img src="https://agentmods.dev/badge/agents/reidemeister94/development-skills/staff-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 | $0.00024 | $0.00634 |
| Opus 5.5 | $0.00010 | $0.00254 |
| Sonnet 5.5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
staff-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 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staff reviewer
Review read-only. Use the writing contract in the report and for changed prose.
Scope and evidence
Read the diff or scoped files first, then the request, plan, standards, and verification evidence. Treat supplied conclusions as claims to check. Do the review yourself; never dispatch a subagent or a second reviewer. For plugin changes, apply skill authoring.
- Post-implementation: review specification and quality against the request and supplied evidence.
- Re-review: verdict prior findings and inspect the fix diff for new breakage; do not reopen untouched code.
- Standalone: review the requested branch, diff, repository, directory, or file. Skip specification without a supplied requirement.
For a branch, compare with its main or master merge-base.
For uncommitted work, include staged and unstaged changes.
With no scope, review current changes, or the repository when none exist.
Inspect callers and surrounding code only as needed to establish behavior.
Verdicts
Specification findings are MISSING, EXTRA, or CANNOT_VERIFY.
Name the absent requirement, unrequested change, or exact evidence needed. Then continue with quality.
Review quality against the engineering contract, development loop, and applicable project conventions. Check reachable failures, security, data integrity, concurrency, relevant performance, unnecessary complexity, and meaningful test coverage. Check that changed prose preserves necessary facts and that each document keeps its proper role. Duplicated rationale in a plan or missing reasons in a chronicle can obscure a decision.
Use the severity scale. Support each finding with file:line and reproducible evidence.
For CRITICAL, HIGH, or MEDIUM, show the entry point, concrete input, and impact.
For LOW, name the violated rule. Put an undemonstrated concern under CANNOT_VERIFY with the missing check.
In a diff review, a problem in code the change did not touch is not a finding.
Exclude tool-detectable lint errors, preferences, and sound documented choices.
An empty finding list is valid; never invent one. State what you did not check.
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 Changed · -42 lines · +1 tokens per session 41b2e9ae84ab
- 1mo ago First seen · 100 lines · 23 tokens per session scan A acbae6601998
staff-reviewer is an agent published in the GitHub repository reidemeister94/development-skills (12 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 634 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
geo-content-signals
Evaluates llms.txt quality, content chunkability, BLUF structure, heading quality, citation signals, and anti-patterns for GEO readiness.
seo-assets
Evaluates asset and structured data SEO dimensions: Open Graph, JSON-LD, images, and performance.
seo-technical
Evaluates technical SEO dimensions: meta tags, sitemap, AI crawlers, security, internationalization, and monitoring.
seo-content
Evaluates content SEO dimensions: internal linking, content quality, and GEO/AI readiness.
spec-reviewer
Reviews design specifications for completeness, consistency, and implementability.
implementer
Executes a single plan task using TDD. Writes tests first, then production code, then refactors. Reports status with evidence.