ratary: Skill for Cursor

.cursor/skills/forge-inspect/SKILL.md

forge-inspect is a skill for Cursor from ontorata/ratary. It costs 25 tokens per session (380 once invoked), scanned A, original, MIT.

A review checkpoint between tasks in the Forge development process. It checks whether code follows the current blueprint and whether its structure and tests meet project rules.

In plain words
What is it for?
Use it after Forge execution tasks and before landing changes. It reviews the relevant diff, architecture boundaries, required tests, and issues that must block or merely be noted.
Why use it?
It catches specification violations and code-quality problems before the next task or release step can continue.

Skill for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents.

This is ontorata/ratary's own configuration. It tells Cursor how to work on ratary itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ratary configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ontorata/ratary. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ontorata/ratary/main/.cursor/skills/forge-inspect/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ontorata/ratary

Made for: Cursor.

Wrote 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.

agentmods badge for forge-inspect

README.md
[![agentmods](https://agentmods.dev/badge/skills/ontorata/ratary/forge-inspect.svg)](https://agentmods.dev/skills/ontorata/ratary/forge-inspect)
Your own site
<a href="https://agentmods.dev/skills/ontorata/ratary/forge-inspect"><img src="https://agentmods.dev/badge/skills/ontorata/ratary/forge-inspect.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00380
Opus 5 $0.00013 $0.00190
Sonnet 5 $0.00005 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 7d ago against content hash ab2c649934be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

forge-inspect 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.

.cursor/skills/forge-inspect/SKILL.md · 47 lines

What it actually says

Forge Inspect

Activates: between forge-execute tasks (and before land).

Two passes

Pass 1 — Spec compliance

  • Diff matches current blueprint task only
  • ADR / phase requirements satisfied
  • No forbidden patterns (11-AI-RULES.md Never create)
  • Inspection Pattern Ledger (Phase 8.8): recall relevant ledger entries via MCP search_memory tag inspection-pattern or REST /api/v1/inspection-patterns?path=… — use as prioritized checklist only; constitutional blockers still come from spec, not ledger alone

Pass 2 — Code quality

Severity

Level Action
constitutional Block — fix before next task
critical Block — fix before next task
major Fix in current task if small; else add blueprint task
minor Note; optional follow-up

Output

## Inspect — Task N
- Spec: PASS / FAIL
- Quality: PASS / FAIL
- Blockers: (list or none)

Prompt cross-ref: docs-ai/cross-cutting/agent-forge/workflow/prompts/review/code-review.md

Optional: launch Bugbot subagent for large diffs when user requests.

Changes

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.

  1. 7d ago First seen · 47 lines · 25 tokens per session scan A ab2c649934be

Subscribe to this mod's changes

forge-inspect is a skill published in the GitHub repository ontorata/ratary (1 stars, last pushed 28d ago), licensed MIT. It adds 25 tokens to every session and 380 once invoked, about $0.0001 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.

Related

Other skills, from other repositories