Borrowing it
Nothing to install: this file belongs to TheK3nsai/ops-brain. 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/TheK3nsai/ops-brain/main/CLAUDE.mdgit clone --depth 1 https://github.com/TheK3nsai/ops-brainWrote 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/thek3nsai/ops-brain/claude-md)<a href="https://agentmods.dev/instructions/thek3nsai/ops-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/thek3nsai/ops-brain/claude-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/thek3nsai/ops-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/thek3nsai/ops-brain/claude-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 | $0.01630 | $0.01630 |
| Opus 5.5 | $0.00652 | $0.00652 |
| Sonnet 5.5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
ops-brain CLAUDE.md scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Prod does not publish `localhost:3000` on the host** — check readiness inside the container (`docker compose -f docker-compose.prod.yml exec -T ops-brain curl -sf http://localhost:3000/ready`) and liveness through th How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ops-brain
Rust MCP server for cross-agent coordination. Rust 2021, rmcp 1.6, PostgreSQL 18 via sqlx, stdio/HTTP transport.
Scope: a small team bus. The MCP surface is handoffs, bounded knowledge, and check-in; machine ingestion, wake polling, and stateless briefings use narrow REST endpoints. Inventory, incidents, monitoring, and ticketing are out of scope by design: hard stops and rationale in ROADMAP.md, shipped history in CHANGELOG.md.
Surface (13 tools)
Tool groups, REST endpoints and the backfill-embeddings subcommand: README.md → Tools. Keep this heading's count equal to the #[tool( stubs in src/tools/mod.rs; a deploy check parses it (GOTCHAS.md).
Identity: interactive sessions use per-agent tokens (OPS_BRAIN_AGENT_TOKENS) or optional external OAuth subject/client bindings. Both bind from_agent server-side and reach /mcp only, never REST; MCP write tools reject mismatching identity. The main bearer stays unbound as operator break-glass. Contracts: docs/agent-tokens.md, docs/oauth.md.
Architecture Constraints
- All
#[tool]stubs MUST remain in the single#[tool_router] impl OpsBrainblock insrc/tools/mod.rs— rmcp macro requirement. Each stub delegates to ahandle_*function in the appropriate category module. - Tool errors return
Ok(CallToolResult::error(...)), neverErr(McpError) - Tool descriptions state what the tool does, when to use it and when not, each parameter, and its caveats; no worked examples or behavioral steering. Under-describing costs more than the tokens saved. Removing a tool means removing its mentions from
get_infotoo — the compiler won't catch those. - Slugs are the public API (not UUIDs) — tools resolve slugs to IDs internally. On miss, pg_trgm suggests similar slugs via
not_found_with_suggestions()in helpers.rs - Tracing writes to stderr (critical: stdout is the MCP stdio transport)
Client-Scope Disclosure Guard
One deployment is one trust domain; client scoping is a knowledge disclosure guard inside it, not tenant isolation. Scoped queries withhold cross-client content unless acknowledge_cross_client: true (audit-logged), and every result carries _client_slug/_client_name provenance. Restricted tokens (exclude_client_data) filter in SQL through Visibility (src/auth.rs): any new read path must thread Visibility through to its query, because a post-fetch filter would short pages and leak counts. Full gate table: docs/client-scope.md; token contract: docs/agent-tokens.md.
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.
- today Changed · +10 tokens per session 6016560a7732
- yesterday Changed · +31 tokens per session adc3414aa237
- 11d ago Changed · -43 lines · -1,429 tokens per session 21b493fd6934
- 12d ago Changed · -5 lines · -36 tokens per session 6c49e7c93325
- 13d ago Changed · +7 lines · +219 tokens per session a6bd07e653cd
- 18d ago Changed · +2 lines · +100 tokens per session ed2030bb3d54
- 1mo ago Changed · -1 lines · -58 tokens per session e52a40d4608b
- 1mo ago Changed · +88 tokens per session f89ada900045
- 1mo ago Changed · -5 tokens per session 9a65b99e87e4
- 1mo ago First seen · 93 lines · 2,710 tokens per session scan A 6c49fedecefa
ops-brain CLAUDE.md is an instructions file published in the GitHub repository TheK3nsai/ops-brain (1 stars, last pushed today), licensed Apache-2.0. It adds 1,630 tokens to every session, about $0.0065 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.