smf-forgewright AGENTS.md

smf-forgewright AGENTS.md is an instructions file for Codex, OpenCode from smfworks/smf-forgewright. It costs 509 tokens per session, scanned A, original, MIT.

A set of instructions for using SMF Forgewright, an AI-assisted tool for automating browser tasks and improving repeatable workflows.

In plain words
What is it for?
Setting up Forgewright, choosing or creating a use case, configuring inputs and outputs, running workflows, and refining their instructions.
Why use it?
It gives the coding agent a defined setup process, safety rules, and questions to ask before running a workflow.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

Install

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.

agentmods
npx agentmods add instructions/smfworks/smf-forgewright/agents-md
Clone the repo
git clone --depth 1 https://github.com/smfworks/smf-forgewright

Made for: Codex, OpenCode.

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 smf-forgewright AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/smfworks/smf-forgewright/agents-md.svg)](https://agentmods.dev/instructions/smfworks/smf-forgewright/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/smfworks/smf-forgewright/agents-md"><img src="https://agentmods.dev/badge/instructions/smfworks/smf-forgewright/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 509 This file is loaded in full into every session.
When invoked 509 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00509 $0.00509
Opus 5 $0.00254 $0.00254
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured 5d ago against content hash 7db8a6fbe966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

smf-forgewright AGENTS.md 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 5d 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent bootstrap: SMF Forgewright

You are assisting a user with SMF Forgewright, an AI-guided browser automation and self-tuning workbench.

Mission

Help the user set up Forgewright, choose a use case, configure sources and outputs, run a Webwright-style workflow, tune the playbook with a SkillOpt-style loop, and optionally wire results into a dashboard.

First actions

  1. Read README.md.
  2. Read docs/forgewright-engineering-guide.md.
  3. Run a setup/health check appropriate for the OS:
    • Windows: powershell -NoProfile -ExecutionPolicy Bypass -File scripts/setup.ps1
    • macOS/Linux: bash scripts/setup.sh
    • Existing environment: forgewright doctor
  4. Run forgewright bootstrap to show setup status, safe demo choices, and the next recommended prompt.
  5. Show the user sample use cases with forgewright examples.
  6. Ask the user which use case to start with, or whether to create a custom one.
  7. Run forgewright init-use-case and walk through the prompts.

Rules

  • Do not embed credentials, tokens, cookies, or private data in files.
  • Do not log into private systems unless the user explicitly authorizes the run.
  • Do not send, post, draft, schedule, purchase, or change external state unless explicitly requested and confirmed.
  • Prefer public unauthenticated sources for first runs.
  • Preserve evidence: screenshots, source URLs, visible dates or evergreen labels, logs, Markdown, JSON, and provenance.
  • Use bounded edits for tuning: maximum three add/delete/replace operations per SkillOpt step.
  • Promote a tuned playbook only after human review of the promotion packet.

Output contract

Every repeatable run should produce:

outputs/<use-case>/plan.md
outputs/<use-case>/final_runs/run_<n>/final_script.py
outputs/<use-case>/final_runs/run_<n>/final_script_log.txt
outputs/<use-case>/final_runs/run_<n>/screenshots/*.png
outputs/<use-case>/final_runs/run_<n>/report.md
outputs/<use-case>/final_runs/run_<n>/data.json

Good default recommendation

Read the full file on GitHub · 48 lines

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. 5d ago First seen · 48 lines · 509 tokens per session scan A 7db8a6fbe966

Subscribe to this mod's changes

smf-forgewright AGENTS.md is an instructions file published in the GitHub repository smfworks/smf-forgewright (5 stars, last pushed 3mo ago), licensed MIT. It adds 509 tokens to every session, about $0.0025 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.