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 sergeyklay/.agents --skill review-specgit clone --depth 1 https://github.com/sergeyklay/.agentsWrote 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/sergeyklay/.agents/review-spec)<a href="https://agentmods.dev/skills/sergeyklay/.agents/review-spec"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/review-spec/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/sergeyklay/.agents/review-spec"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/review-spec.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 | $0.00165 | $0.02431 |
| Opus 5 | $0.00082 | $0.01215 |
| Sonnet 5 | $0.00033 | $0.00486 |
| Haiku 4.5 | $0.00016 | $0.00243 |
Grade A, and why
review-spec 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 7d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specification Architectural Review
You are conducting a deep architectural review of a specification or design document — before implementation begins. You answer one question: is this spec ready to be implemented, and if not, what must change?
A spec is the contract between an architect and an implementer. Every ambiguity, every unstated assumption, every quality-attribute trade-off the spec leaves implicit will surface as a defect during implementation or in production. Your review is the last gate before implementation begins; the cost of catching issues at this stage is orders of magnitude lower than catching them after code is written.
Input
The user provides two arguments:
- Task name — a brief description of the feature ("Implement worker attempt function") OR a GitHub issue reference (
https://github.com/owner/repo/issues/123,owner/repo#123,#123). - Spec path — a markdown file defining the architecture or design.
If the invoker has already quoted the issue title and body in this prompt (typical when an orchestrator fetched the tracker in an earlier phase and passed the context forward), use those values directly — do not re-fetch. Otherwise, if the task name is a GitHub issue reference, fetch context with gh issue view <ref> --json title,body, and use the fetched title as the task name and the body as additional context. If the argument is plain text and no issue context was provided, treat it as the task name verbatim.
Workflow
The review proceeds in five phases. Each phase has a documented gate that prevents a specific failure mode (ungrounded reviews, missed conventions, ambiguity blindness, severity inflation). Do not skip, merge, or abbreviate any phase.
Copy this checklist into your response and mark items as you complete them:
- Phase 1 — Resolve task reference
- Phase 2 — Build project context
- Phase 3 — Read the specification thoroughly
- Phase 4 — Evaluate against six dimensions
- Phase 5 — Compose the review
What ships with it
3 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.
- 7d ago Changed · -4 tokens per session a3a0b912cd40
- 11d ago First seen · 120 lines · 169 tokens per session scan A af4b1a552fe0
review-spec is a skill published in the GitHub repository sergeyklay/.agents (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 165 tokens to every session and 2,431 once invoked, about $0.0008 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 skills, from other repositories
chatdoc-studio-api
ChatDOC Studio API usage guide - complete documentation and examples for PDF parsing, chat applications, agent applications, content retrieval, and data extraction APIs.
war-room
Multi-agent research war room. Personas debate in sequential turns through two phases — ideation and proposal writing. Persona persistence and drift detection are enforced every turn via the persistent-persona skill.
system-info
Probe system resources — CPU, RAM, disk, GPU/CUDA/MPS — and translate findings into experiment design recommendations. Run this at the start of any compute-intensive project.
persistent-persona
Mechanism for keeping an agent anchored to a caller-defined persona across sessions. Covers the biplate private memory system for drift detection and self-correction.
memory-checkpoint
Defines how to save and load agent state as checkpoint files.
ChatDOC Studio--KnowledgeMate
Create and operate ChatDOC Studio knowledge bases through pdrouter using a Bearer API key and JavaScript helpers. Use when Codex needs to upload one or more PDF/DOC/DOCX files, skip failed files without aborting the whole job, create a knowledge base from successful uploads, or call the ChatDOC Studio knowledge-base…