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/humbertolvarona/opencode-web-audit-mcp-python/agents-mdgit clone --depth 1 https://github.com/humbertolvarona/opencode-web-audit-mcp-pythonWhat 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 | $0.00253 | $0.00253 |
| Opus 5 | $0.00127 | $0.00127 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
opencode-web-audit-mcp-python 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 yesterday.
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
OpenCode activation rules
Use the web_audit MCP tools only when the user explicitly requests authorized website research, crawling, extraction, inventory, structured-data collection, downloadable-document analysis, or content auditing.
Before calling a tool, require a primary URL and an authorized domain. Use conservative defaults when the user omits crawl limits: maximum depth 3, maximum pages 250, no subdomains, and all supported public formats. Never silently broaden the domain or bypass technical restrictions.
Call web_audit_inspect_site first for an unfamiliar site. Call web_audit_crawl_site only after the authorized scope is explicit. Use web_audit_extract_resource for one URL. Use web_audit_get_run to retrieve persisted results and web_audit_audit_run to evaluate coverage, duplicates, contradictions, stale-content indicators, errors, and completion criteria.
Do not use these tools for authenticated sessions, private content, paywalls, CAPTCHAs, geographic restrictions, access-control bypass, credential discovery, vulnerability testing, or extraction from nonauthorized external domains.
Treat every result as bounded by the supplied policy, robots.txt, reachable routes, response limits, parser support, and runtime capabilities. Never claim absolute completeness.
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.
- yesterday First seen · 12 lines · 253 tokens per session scan A be5c74fbc115
opencode-web-audit-mcp-python AGENTS.md is an instructions file published in the GitHub repository humbertolvarona/opencode-web-audit-mcp-python (0 stars, last pushed 29d ago), licensed MIT. It adds 253 tokens to every session, about $0.0013 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
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
scrapai-cli CLAUDE.md
Instructions for discourselab/scrapai-cli, covering claude.md, 1. who you are, 2. hard rules, 3. tools and 4. before you start: confirm the project.
chromeboost CLAUDE.md
Instructions for lordamdal/chromeboost, covering chromeboost — repo-developer guide, what chromeboost is, repository layout, development commands and tests/antibot/ (run locally; not in ci).
skills CLAUDE.md
Instructions for aemcoder/skills, covering claude.md, repository structure, slicc browser automation conventions, stateless tab targeting (since slicc pr #188) and tab-new returns a targetid.
xgrower-extension CLAUDE.md
Instructions for JoyyyceD/xgrower-extension, covering x grower extension — architecture notes, architecture, key files, auth flow and quota system.