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/ffroliva/gflow-cli/copilot-instructionsgit clone --depth 1 https://github.com/ffroliva/gflow-cliWhat 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 | $0.00243 | $0.00243 |
| Opus 5 | $0.00121 | $0.00121 |
| Sonnet 5 | $0.00049 | $0.00049 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade A, and why
gflow-cli 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 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.
What it actually says
Copilot Code Review Instructions
Review this repository as a Python CLI that automates browser-authenticated Google Flow workflows. Treat auth, browser automation, CI, release, and secret handling changes as high-risk even when the diff is small.
For pull request reviews:
- Check that PRs target
develop, unless they are release PRs. - Flag unclear contributor provenance, missing DCO sign-off, placeholder author emails, and any copied private data.
- Look for leaked tokens, cookies, signed URLs, local profile paths, and captured Google/Flow request data.
- For auth/browser changes, check that the implementation preserves profile isolation, does not weaken local path boundaries, and avoids remote debugging unless explicitly documented.
- For CI changes, check forked-PR secret behavior and avoid recommending
pull_request_targetfor jobs that checkout or execute contributor code. - For behavior changes, expect focused tests and docs/changelog updates.
- Keep findings concrete: reference files/lines, explain the user-visible risk, and separate blocking issues from cosmetic suggestions.
Do not approve pull requests. Copilot review is advisory; maintainer approval is still required.
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 · 25 lines · 243 tokens per session scan A 1c935848926c
gflow-cli copilot-instructions.md is an instructions file published in the GitHub repository ffroliva/gflow-cli (136 stars, last pushed 2d ago), licensed MIT. It adds 243 tokens to every session, about $0.0012 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
agentic_design_patterns AGENTS.md
Instructions for gtesei/agentic_design_patterns, covering agents.md, 1. repository purpose & layout, 2. running examples, python and typescript.
agentic-playwright ai-native-workflow.instructions.md
Instructions for idavidov13/agentic-playwright, covering ai-native workflow, critical, main workflow (8 phases), phase 4 — confidence-gate format (mandatory) and proposal.
agentic-playwright selectors.instructions.md
Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.
toh-framework CLAUDE.md
Instructions for wasintoh/toh-framework, covering claude.md — toh framework (repo development guide), what this is, everyday commands, verification protocol and single source, transformed per ide.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
featherspec memory-bank.instructions.md
FeatherSpec Memory Bank writing rules (thin loader).