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.
curl -O https://raw.githubusercontent.com/ontorata/ratary/main/.cursor/skills/forge-execute/SKILL.mdgit clone --depth 1 https://github.com/ontorata/rataryWrote 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/ontorata/ratary/forge-execute)<a href="https://agentmods.dev/skills/ontorata/ratary/forge-execute"><img src="https://agentmods.dev/badge/skills/ontorata/ratary/forge-execute/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/ontorata/ratary/forge-execute"><img src="https://agentmods.dev/badge/skills/ontorata/ratary/forge-execute.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 | $0.00026 | $0.00254 |
| Opus 5.5 | $0.00010 | $0.00102 |
| Sonnet 5.5 | $0.00005 | $0.00051 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
forge-execute 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 2mo 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.
What it actually says
Forge Execute
Activates: blueprint approved.
Modes
A — Sequential checkpoints (default)
- Take next unchecked task from
{slug}-plan.md - Run
forge-provefor that task (tests first when behavior changes) - Run
forge-inspectbefore marking task done - Commit with single-intent message; update plan checkbox
- Pause for owner on ambiguous scope creep
B — Subagent per task
- Dispatch one subagent with: task text, file paths, constitution link, verify command
- Review output with two passes: (1) spec match to task, (2) code quality / layers
- Parent agent integrates; never merge unreviewed subagent diffs blindly
Rules
- One concern per commit
- No drive-by refactors
- Stop on red tests — invoke
forge-diagnose - Update phase docs only when task explicitly requires it
Progress
Report after each task: files touched, tests run, commit hash.
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.
- 2mo ago First seen · 37 lines · 26 tokens per session scan A 80dfbf3da3b2
forge-execute is a skill published in the GitHub repository ontorata/ratary (1 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 254 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 2026-08-31.
Other skills, from other repositories
gsd-quick-batch
Batch several /skill:gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-pause-work
Create context handoff when pausing work mid-phase.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
eng-delivery
Deliver work in the compozy/compozy repository. Use when dispatching or supervising sessions, opening or updating a PR, filing an issue, handling review feedback or CI, or declaring work done. Excludes product behavior of the shipped spec-cycle agents.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.