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 agentmods add instructions/smfworks/smf-forgewright/agents-mdgit clone --depth 1 https://github.com/smfworks/smf-forgewrightWrote 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/instructions/smfworks/smf-forgewright/agents-md)<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>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 | $0.00509 | $0.00509 |
| Opus 5 | $0.00254 | $0.00254 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
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.
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
- Read
README.md. - Read
docs/forgewright-engineering-guide.md. - 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
- Windows:
- Run
forgewright bootstrapto show setup status, safe demo choices, and the next recommended prompt. - Show the user sample use cases with
forgewright examples. - Ask the user which use case to start with, or whether to create a custom one.
- Run
forgewright init-use-caseand 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
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.
- 5d ago First seen · 48 lines · 509 tokens per session scan A 7db8a6fbe966
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).