tuicr is a terminal interface for reviewing code changes, with Vim-style navigation, inline comments, and review tracking. It is used to inspect uncommitted changes, commit ranges, or pull requests from GitHub, GitLab, and Bitbucket, and can export reviews or markdown. Its catalogue entries provide instructions and a skill for working with the tool.
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/agavra/tuicr/copilot-instructionsgit clone --depth 1 https://github.com/agavra/tuicrWrote 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/agavra/tuicr/copilot-instructions)<a href="https://agentmods.dev/instructions/agavra/tuicr/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/agavra/tuicr/copilot-instructions.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 | $0.01039 | $0.01039 |
| Opus 5 | $0.00519 | $0.00519 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
tuicr copilot-instructions.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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tuicr — Copilot Instructions
tuicr is a Rust terminal UI application for reviewing diffs (AI-generated or otherwise) like a GitHub pull request, directly from the terminal.
Build, test, lint
cargo build
cargo test
cargo fmt
cargo clippy -- -D warnings # CI enforces -D warnings
Run a single test by name:
cargo test test_name_fragment # matches any test whose name contains the fragment
Architecture
Central state: App (src/app.rs)
All UI state lives in App. It holds the VCS backend, the parsed diff files, the review session, scroll/cursor positions, and the current InputMode. Everything in the render and event loop reads from App.
Input flow
crossterm Event → map_key_to_action(key, InputMode) → Action enum → handler in src/handler/
Each InputMode has its own handler (handle_diff_action, handle_command_action, etc.). Actions are defined in src/input/keybindings.rs.
VCS abstraction (src/vcs/)
VcsBackend trait in src/vcs/traits.rs abstracts Git, Mercurial, and Jujutsu. detect_vcs() in src/vcs/mod.rs auto-detects (jj → git → hg). Git has two backends: libgit2 (default) and a CLI fallback used automatically for sparse checkouts, or forced via backend = "cli" in config.
DiffFormat::Hg and DiffFormat::GitStyle share the text parser in src/vcs/diff_parser.rs. Native Git uses libgit2 directly.
Forge integration (src/forge/)
ForgeBackend trait in src/forge/traits.rs. Only GitHub is implemented (v1), via the gh CLI — not a REST/GraphQL SDK. All gh invocations go through GhCommandRunner in src/forge/github/gh.rs.
Thread boundary rule: network calls happen on a background thread; diff parsing and state mutations happen on the main thread. SyntaxHighlighter is not Send. Background threads return plain Send-safe data; finish_* functions on the main thread do the parsing.
Persistence
Sessions are JSON files at ~/.local/share/tuicr/reviews/. Loaded by find_session_for_repo() on startup. Config is at ~/.config/tuicr/config.toml (XDG, or %APPDATA%\tuicr\config.toml on Windows). Unknown config keys produce startup warnings, not errors.
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.
- 5d ago First seen · 86 lines · 1,039 tokens per session scan A 45a1b6dde72f
tuicr copilot-instructions.md is an instructions file published in the GitHub repository agavra/tuicr (3,029 stars, last pushed 2d ago), licensed MIT. It adds 1,039 tokens to every session, about $0.0052 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 2026-08-30.
Other instructions, from other repositories
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
pupila CLAUDE.md
Instructions for FranRom/pupila, covering claude.md, where things live, stack, run locally and repo layout.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.