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/nick-pape/grackle/agents-mdgit clone --depth 1 https://github.com/nick-pape/grackleWrote 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/nick-pape/grackle/agents-md)<a href="https://agentmods.dev/instructions/nick-pape/grackle/agents-md"><img src="https://agentmods.dev/badge/instructions/nick-pape/grackle/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 | $0.04912 | $0.04912 |
| Opus 5 | $0.02456 | $0.02456 |
| Sonnet 5 | $0.00982 | $0.00982 |
| Haiku 4.5 | $0.00491 | $0.00491 |
Grade A, and why
grackle 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 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.
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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grackle Development Guidelines
Self-Updating Documentation
When you encounter unexpected issues, workarounds, or non-obvious behavior (CI quirks, tooling gotchas, environment-specific problems), update this AGENTS.md with the finding so future sessions don't repeat the investigation. Add the note to the most relevant existing section, or create a new one if needed.
Package READMEs
Each package under packages/ has a README.md that is published to npm. When you change a package's public behavior (new commands, renamed options, new MCP tools, new API methods, changed configuration, etc.), update that package's README to match. Do not let READMEs drift out of sync with the code.
- CLI (
packages/cli/README.md): documents every command, subcommand, and flag. Update when adding/removing/renaming commands or options. - MCP (
packages/mcp/README.md): documents every MCP tool with parameters. Update when adding/removing/renaming tools. - Knowledge Core (
packages/knowledge-core/README.md): detailed API reference. Update when the public API changes. - All other packages: concise overviews. Update if the package's purpose, key concepts, or usage instructions change.
Do not update the root README.md as part of this process — it is a separate marketing/overview document maintained independently.
Environment Variables
The root .env.example documents every supported environment variable with defaults and descriptions. When you add, remove, or rename a process.env read, update .env.example to match.
Git Workflow
- Never push directly to main. All changes must go through a pull request. Always create a feature branch and open a PR — never commit and push to
main. - Never rebase or force-push. To sync with
main, first rungit fetch originand then usegit merge origin/maininstead ofgit rebase. Rebasing published branches rewrites history and typically requires a force-push, which we do not allow. - Never merge PRs unless the user explicitly tells you to merge. Other agents may be coordinating merge order.
- Branch naming:
<github-username>/<issue>-<feature>when working on a GitHub issue (where<issue>is the numeric issue id, e.g.,nick-pape/149-agent-subtask-creation), or<github-username>/<feature>when there's no issue (e.g.,nick-pape/fix-typo-in-readme).
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 · 258 lines · 4,912 tokens per session scan A 207917c7dd40
grackle AGENTS.md is an instructions file published in the GitHub repository nick-pape/grackle (21 stars, last pushed 2mo ago), licensed MIT. It adds 4,912 tokens to every session, about $0.0246 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
intelligent-terminal agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
intelligent-terminal rust-localization.instructions.md
Instructions for microsoft/intelligent-terminal, covering localization instructions for rust wta (yaml locale files), file structure, file format, the en-us.yml source file and non-translatable token rules.
intelligent-terminal localization.instructions.md
Instructions for microsoft/intelligent-terminal, covering localization instructions for .resw resource files, components with localized resources, locale categories, authoritative locale list (from terminalapp) and adding or updating localized strings.
intelligent-terminal copilot-instructions.md
Copilot instructions for microsoft/intelligent-terminal, covering copilot instructions for windows terminal, build, running, test and code formatting.
intelligent-terminal instructions.instructions.md
Guidelines for creating high-quality custom instruction files for GitHub Copilot.
intelligent-terminal AGENTS.md
AGENTS.md instructions for microsoft/intelligent-terminal, covering intelligent terminal, architecture, supported agents and settings, user-facing behavior and key files.