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/affromero/gitpane/agents-mdgit clone --depth 1 https://github.com/affromero/gitpaneWhat 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 | $0.01136 | $0.01136 |
| Opus 5 | $0.00568 | $0.00568 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
gitpane 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 2d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working on gitpane, a multi-repo Git workspace dashboard TUI (Rust, ratatui). For the human-facing overview, see README.md.
Setup
- Rust edition 2024, MSRV 1.88.0. Install a matching toolchain (rustup recommended).
- No services or network access are needed to build, run, or test.
- Optional tooling for the full local suite:
cargo install cargo-audit cargo-llvm-cov, plusjustfor the task recipes below.
Build and run
just run # or: cargo run
cargo build --release
Checks (run before every commit)
just ci # fmt + lint + docs + test, the full gate
# or individually:
just fmt # cargo fmt --all
just lint # cargo clippy --all-targets --all-features -- -D warnings
just test # cargo test --all-targets --all-features
just docs # rustdoc with -D warnings
CI runs the same checks and treats every warning as an error, so just ci must
pass before you push. Tests are inline #[cfg(test)] modules in the binary
target, so a plain cargo test --lib finds nothing. Use just test or
cargo test --bin gitpane.
Pre-commit hooks (required)
Install them before contributing:
pre-commit install # installs the pre-commit and pre-push hooks
The pre-commit hook runs file hygiene, TOML/YAML checks, cargo fmt, cargo clippy, and the two project rules below. The pre-push hook runs tests, audit,
docs, and coverage.
Hard constraints
- Every source file stays under 1000 lines. When a file approaches the limit,
split it: turn
foo.rsinto afoo/directory module and re-export the public items fromfoo/mod.rsso external paths such ascrate::foo::Bardo not change. Do not add exclude lists to dodge the limit; split the file. - Every directory under
src/holds at most 10 files. Group related modules into a subfolder rather than letting a folder sprawl. A subfolder's files count toward the subfolder, not its parent. - No warnings. clippy runs with
-D warnings. Fix the cause; do not paper over it with#[allow(...)]unless there is a documented reason. - Refactors that relocate code must be behavior preserving: keep the move mechanical, re-export to preserve public paths, and keep the test count identical.
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.
- 2d ago First seen · 104 lines · 1,136 tokens per session scan A a952e4c99921
gitpane AGENTS.md is an instructions file published in the GitHub repository affromero/gitpane (130 stars, last pushed 3d ago), licensed MIT. It adds 1,136 tokens to every session, about $0.0057 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
Vibe-Research AGENTS.md
Instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.
vizro copilot-instructions.md
Copilot instructions for mckinsey/vizro, covering github copilot instructions for vizro, pull requests from bots and automated tooling and everything else.
TreeMap-Disk-Visualizer AGENTS.md
Instructions for Prithvi-Web/TreeMap-Disk-Visualizer, covering treemap for agents, two ways in, the core workflow: scan → inspect → dry-run → act, the safety model (enforced server-side, not advisory) and mcp specifics.
openclaw-dashboard CLAUDE.md
Instructions for mudrii/openclaw-dashboard, covering go development standards, project constraints, internal packages, environment and commands.
neko-master copilot-instructions.md
Instructions for foru17/neko-master: All repo guidance lives in AGENTS.md — commands, code conventions, key contracts, and the project map. Follow it.