Borrowing it
Nothing to install: this file belongs to wolverin0/wezbridge. 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/wolverin0/wezbridge/main/AGENTS.mdgit clone --depth 1 https://github.com/wolverin0/wezbridgeWrote 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/wolverin0/wezbridge/agents-md)<a href="https://agentmods.dev/instructions/wolverin0/wezbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/wolverin0/wezbridge/agents-md/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/instructions/wolverin0/wezbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/wolverin0/wezbridge/agents-md.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 | $0.02172 | $0.02172 |
| Opus 5.5 | $0.00869 | $0.00869 |
| Sonnet 5.5 | $0.00434 | $0.00434 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
wezbridge 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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wezbridge custody, verified delivery and runtime boundaries; scoped context and proportional impact analysis.
Wezbridge agent contract
Role and custody
- The operator selects the orchestration agent. Resolve the live owner by project and verified pane identity; do not hardcode Claude/pane 0 or Codex/pane 33.
- The reasoning agent handles decisions and acceptance. The existing daemon owns durable wake delivery and missing-owner recovery; do not create another watcher per conversation.
- A launch profile selects a session/model for recovery only. It does not grant task, merge, deployment or credential authority.
- Project agents retain ownership of their repositories. Use isolated worktrees and declared ownership for changes; preserve shared uncommitted files.
Read and execute
- When consulting project documents, use
DOCS-MAP.mdto resolve authority. Readdocs/operations.mdfor operation/recovery anddocs/a2a-protocol.mdfor peer messages; unrelated edits do not require both. - Use bounded MemoryMaster recall for architectural decisions. Check a relevant code index when useful; current code and runtime evidence resolve disagreements.
- Keep the current task in its existing roadmap and Fleet card. Use linked attempts for retries, not a second backlog or duplicated operator decision.
- Infer routine technical steps inside the user's authorized scope. Return questions only for a material unresolved decision, with evidence and a recommendation.
- Use the operator's bounded delegation policy in the global contract when higher-priority runtime rules permit it. Existing peer tasks keep their recorded scope; status messages do not widen authority.
Delivery and acceptance
- Prefer
a2a_sendand inspect its submission/delivery result. For rawsend_prompt, follow the operator's current submission rule; never resend the body to repair an Enter. - Verify the target project/pane and an available composer. Never type shell commands into an agent TUI.
- Track pending work across turns. Codex requesters poll outstanding peers at a bounded cadence; responders ACK, send progress and return a result with criteria, files_changed and next_action.
- Transport receipt is not acceptance. Open the referenced evidence and match objective, repository, revision and required criteria before accepting work.
- A failed, missing or contradictory mandatory criterion prevents closure. Preserve failure evidence and request bounded remediation.
- The implementation author does not independently approve their own change. Keep the review and origin-acceptance roles explicit.
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.
- 1mo ago Changed · +27 tokens per session 5a80e5a92684
- 1mo ago Changed · -30 lines · -84 tokens per session 22fe0edfe309
- 1mo ago Changed 70185265b3d5
- 2mo ago First seen · 172 lines · 2,229 tokens per session scan A af4592db7fe9
wezbridge AGENTS.md is an instructions file published in the GitHub repository wolverin0/wezbridge (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,172 tokens to every session, about $0.0087 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.