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/kenn-io/roborev/agents-mdgit clone --depth 1 https://github.com/kenn-io/roborevWrote 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/kenn-io/roborev/agents-md)<a href="https://agentmods.dev/instructions/kenn-io/roborev/agents-md"><img src="https://agentmods.dev/badge/instructions/kenn-io/roborev/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 | $0.04520 | $0.04520 |
| Opus 5 | $0.02260 | $0.02260 |
| Sonnet 5 | $0.00904 | $0.00904 |
| Haiku 4.5 | $0.00452 | $0.00452 |
Grade B, and why
roborev AGENTS.md scanned grade B 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 4d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Release workflow testing must not publish anything. Do not run any command, workflow mode, or release tool path that creates public How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
This repo hosts roborev, a local daemon + CLI for AI-assisted code review. Use this guide to navigate the codebase quickly, understand subsystem boundaries, and avoid missing adjacent changes when working in a growing Go project.
Start Here
- Product behavior and user-facing workflows:
README.md - CLI entry point and command registration:
cmd/roborev/main.go - Command discovery:
rg '^func .*Cmd\(' cmd/roborev - Daemon HTTP API and route wiring:
internal/daemon/server.go - Worker pool and job execution:
internal/daemon/worker.go - SQLite schema and migrations:
internal/storage/db.go - Config loading and resolution:
internal/config/config.go - Prompt construction:
internal/prompt/prompt.go - TUI entry point:
cmd/roborev/tui/tui.go
Architecture At A Glance
CLI (roborev) -> HTTP API -> Daemon -> Worker Pool -> Agent adapters
| |
| -> Hooks / Activity log / CI poller
|
-> SQLite DB <-> Sync worker <-> PostgreSQL (optional)
- The daemon is the long-lived control plane. Many CLI commands are thin HTTP clients.
- Background daemon work must not edit tracked source files in the user's checked-out working tree or apply agent changes there. Repo metadata is different:
roborev initmay update the usually tracked.gitignoreso the configuredsnapshot_dir(default.roborev/) is ignored, and daemon review work may create disposable ignored snapshot artifacts there so sandboxed agents can read oversized diffs. Runtime snapshot creation may also add a local.git/info/excludefallback when an existing checkout is missing the ignore rule. - Foreground agentic flows such as
roborev fixandroborev refinemay modify code. - Isolated background fix work uses temporary git worktrees and stores patches in the DB.
Package Map
| Path | Purpose | Start with |
|---|---|---|
cmd/roborev/ |
Cobra CLI commands and daemon-facing client logic | main.go, review.go, fix.go, refine.go, analyze.go, daemon_cmd.go |
cmd/roborev/tui/ |
Bubble Tea terminal UI | tui.go, api.go, fetch.go, handlers.go, render_*.go |
internal/daemon/ |
HTTP server, handlers, worker pool, SSE, hooks, runtime, CI poller | server.go, worker.go, client.go, runtime.go, ci_poller.go |
internal/storage/ |
SQLite models/queries/migrations, sync logic, PostgreSQL mirror | db.go, models.go, jobs.go, reviews.go, sync.go, postgres.go |
internal/agent/ |
Agent interface, registry, command-backed implementations, ACP support | agent.go, codex.go, claude.go, acp.go, test_agent.go |
internal/config/ |
Global config, repo config, validation, key metadata, resolve helpers | config.go, keyval.go |
internal/prompt/ |
Review prompt builder and template loading | prompt.go, templates.go, prompt/analyze/ |
internal/review/ |
Daemon-free batch review, synthesis, comment sizing/formatting | batch.go, synthesis.go, result.go |
internal/git/ |
Shared git helpers for refs, diffs, branch logic, repo discovery | git.go |
internal/worktree/ |
Temporary worktree creation, patch capture/apply/check | worktree.go |
internal/skills/ |
Embedded Codex/Claude skill files and installer logic | skills.go, internal/skills/claude/, internal/skills/codex/ |
internal/streamfmt/ |
Formatting streamed agent output for CLI and TUI | streamfmt.go, render.go |
internal/githook/ |
Hook install/upgrade logic | githook.go |
internal/github/ |
GitHub REST helpers used by CI/comment flows | comment.go |
internal/ghaction/ |
GitHub Actions integration | ghaction.go |
internal/update/ |
Self-update logic and release fetches | update.go |
internal/testenv/ |
Test environment setup helpers | testenv.go |
internal/testutil/ |
Temp git repos and shared test helpers | git.go, testutil.go |
docs/plans/ |
Design notes for larger features | open the matching date/topic file |
skills/ |
Human-readable skill docs shipped to agents | README.md and roborev-*.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.
- 4d ago First seen · 279 lines · 4,520 tokens per session scan B 41a93eb4dcf3
roborev AGENTS.md is an instructions file published in the GitHub repository kenn-io/roborev (1,685 stars, last pushed yesterday), licensed MIT. It adds 4,520 tokens to every session, about $0.0226 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
spec-kit AGENTS.md
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.
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.
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 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).
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.