Borrowing it
Nothing to install: this file belongs to bpauli/gccli. 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/bpauli/gccli/main/AGENTS.mdgit clone --depth 1 https://github.com/bpauli/gccliWrote 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/bpauli/gccli/agents-md)<a href="https://agentmods.dev/instructions/bpauli/gccli/agents-md"><img src="https://agentmods.dev/badge/instructions/bpauli/gccli/agents-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/bpauli/gccli/agents-md"><img src="https://agentmods.dev/badge/instructions/bpauli/gccli/agents-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 | $0.00637 | $0.00637 |
| Opus 5.5 | $0.00255 | $0.00255 |
| Sonnet 5.5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
gccli 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 14d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Rules for agents that change this repository. Build, style, test and documentation rules are in CLAUDE.md.
Verify every PR before it merges
Each PR gets one independent verifier: an agent that did not write the change. The verdict decides the merge. CI and passing tests do not replace it.
The verifier:
- Checks out the exact head SHA in its own worktree, and the base SHA in a second one when it compares behavior.
- Runs
make toolsin each new worktree, then the gate on the head:make fmt-check,make lint,go vet -tags e2e ./...andmake test. When the local Go is newer than thegoline ingo.mod, setGOTOOLCHAIN=go<that version>formake toolsandmake lint. - Runs the real binary from base and head (
go build -o bin/gccli ./cmd/gccli) against a local HTTPS mock, on Linux. PointHTTPS_PROXYandSSL_CERT_FILEat the mock. Set bothHOMEandXDG_CONFIG_HOMEto a temp directory, because gccli reads its config and file keyring fromXDG_CONFIG_HOMEon Linux, and the real one holds the owner's login. UseGCCLI_KEYRING_BACKEND=fileand a token fromauth import. For a refactor, stdout, stderr and the exit code must match base byte for byte. For a behavior change, every difference must be one the PR names. - Injects the defect that each new test claims to catch, and confirms the test fails. Runs these tests, like every test run, with
HOMEandXDG_CONFIG_HOMEset to a temp directory, because mutated test code can reach the real config. - Reruns the claims in the PR's Verification section that are cheap to rerun.
- Makes live Garmin calls only when the account owner approves them for that PR.
- Posts one PR comment that starts with
**Independent verification: PASS**,PASS+NOTESorFAIL, and names the head and base SHA it checked.
Merge only on PASS or PASS+NOTES, and only when every CI check on the verified head has passed, the darwin job too. Merge with gh pr merge <n> --merge --match-head-commit <verified head>. When main moved after the verdict, build and test main plus the PR before the merge. A new head needs a new verdict. A FAIL goes back to a fresh fix round and then a fresh verifier.
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.
- 14d ago First seen · 25 lines · 637 tokens per session scan A 3258f83e2bac
gccli AGENTS.md is an instructions file published in the GitHub repository bpauli/gccli (31 stars, last pushed yesterday), licensed MIT. It adds 637 tokens to every session, about $0.0025 per session on Opus 5.5. 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 2026-10-16.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.