Borrowing it
Nothing to install: this file belongs to Giskard-AI/giskard-skills. 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/Giskard-AI/giskard-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/Giskard-AI/giskard-skillsWrote 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/giskard-ai/giskard-skills/agents-md)<a href="https://agentmods.dev/instructions/giskard-ai/giskard-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/giskard-ai/giskard-skills/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/giskard-ai/giskard-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/giskard-ai/giskard-skills/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 | $0.00780 | $0.00780 |
| Opus 5.5 | $0.00312 | $0.00312 |
| Sonnet 5.5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
giskard-skills 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 1mo 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintaining skills and plugin support
Skill changes
- Each skill has its own directory containing
SKILL.md, with YAML frontmatter that includes a uniquenamematching the directory name and a nonemptydescription. Keep supporting references and scripts inside that directory so installations remain self-contained. - When adding, renaming, or removing a skill, update the available-skills table in
README.mdand theskillsarray in both.claude-plugin/plugin.jsonand.grok-plugin/plugin.json. - The two manifests must remain identical. List individual skill directories (for example
./hub/hub-agent-setup), never parent collections such as./hub/. Grok's indexer does not recursively discover skills from those collection paths. - When updating a skill, review its dependencies, credentials, and network behavior against the README and update that documentation if needed.
- Keep plugin versions synchronized. Bump the plugin version for a release that changes shipped skills or resources; also update the changed skill's
metadata.versionwhen applicable. CI-only changes do not require a plugin version bump.
Validation
Follow the commands in the README's Development checks section. .github/workflows/plugin-smoke.yml runs shared packaging checks, Claude's validator, Grok's indexer, and npx skills installation checks on pull requests and pushes to main. Use uv to manage Python and the smoke-test dependencies; CI uses Python 3.14 and Node.js 24 LTS.
- Packaging checks require the manifests to include every tracked
SKILL.mdexactly once. Add new skill files to Git's index before running the checks; the snapshots use the current contents of tracked files, including uncommitted edits. - Verify discovery with the real provider tooling. Do not replace those checks with a homemade approximation of a provider's loader.
- The skills CLI check installs into a temporary project for Claude Code, Cursor, and Grok and compares every tracked skill file, including references and scripts, with the installed copy.
- Keep smoke tests free of model calls, service credentials, live exports, and tunnels. They verify packaging and discovery, not whether an agent follows the skill correctly. They must not install skills globally or modify the developer's agent configuration.
- External tools are pinned: Claude and the Grok indexer in the workflow, the skills CLI in
scripts/smoke_plugins.py, and Python dependencies inscripts/requirements-smoke.txt. Update pins deliberately and rerun the relevant checks. - Pin every external GitHub Action to a full release commit SHA with a version comment. When updating, verify the release tag resolves to that commit and the commit contains
action.yml. A release such asv10.2.0does not guarantee av10alias exists.
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.
- 1mo ago First seen · 29 lines · 780 tokens per session scan A d5c4d4ec8609
giskard-skills AGENTS.md is an instructions file published in the GitHub repository Giskard-AI/giskard-skills (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 780 tokens to every session, about $0.0031 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 2026-09-24.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.