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/guipegoraro/opencode-bridge/agents-mdgit clone --depth 1 https://github.com/Guipegoraro/opencode-bridgeWhat 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 | $0.01416 | $0.01416 |
| Opus 5 | $0.00708 | $0.00708 |
| Sonnet 5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
opencode-bridge 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
opencode-bridge
MCP server that lets Claude Code delegate coding tasks to external models running on a
local opencode serve. Goal: use cheaper models for implementation work, keeping the main
model for planning and review.
Claude Code --MCP stdio--> opencode-bridge --HTTP/SSE--> opencode serve --> delegated model
v2 architecture
Rebuilt to fix three chronic failures: sessions would freeze silently, delegations came back empty, and the status field lied. In ten lines:
- Completion by event (SSE): the bridge listens to
GET /eventand concludes onsession.idle— the primary signal, measured. Polling/session/statusis only a safety net, with a double-check (status + stable tool-call count + stable completion timestamp). - Scope by directory: every read endpoint on the serve is filtered by
?directory=. The bridge resolves the real scope viaGET /session/{id}(the only endpoint that is not filtered) and repeats it on every subsequent call. Readdocs/APRENDIZADOS.md§3 before touching any HTTP call. - Hard wait ceiling (45 min,
OPENCODE_MAX_POLL_MS): there is never an eternal hang; when it gives up, the bridge says explicitly that it gave up on the wait, not on the session. - Empty-response retry (refetch + one conditional nudge) and error classification on both legs — a session that dies with an error comes back as an error, never a silent empty success.
- Self-heal: serve down → the bridge revives it through the scheduled task and retries the call.
- Auth: mandatory Basic Auth, credential read at runtime from
%USERPROFILE%\.config\opencode\serve-auth.json. No secret in source. - Single source of MCPs:
scripts/sync-opencode-config.ps1generates themcpblock ofopencode.jsonfrom the Claude Code config, with the exception map declared insync-overrides.json(gitignored; example insync-overrides.example.json). - Canary: if a wait concludes via polling without ever having seen
busy, the bridge shouts in the log — the status gate may be blind.
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 · 94 lines · 1,416 tokens per session scan A 7aeed3d181c3
opencode-bridge AGENTS.md is an instructions file published in the GitHub repository Guipegoraro/opencode-bridge (0 stars, last pushed 20d ago), licensed MIT. It adds 1,416 tokens to every session, about $0.0071 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.