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/microsoft/hve-core/ci-owned-validationgit clone --depth 1 https://github.com/microsoft/hve-coreWhat 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 | $0.00674 | $0.00674 |
| Opus 5 | $0.00337 | $0.00337 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
hve-core ci-owned-validation.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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI-Owned Validation Instructions
Keep ordinary local validation predictable while preserving direct, named reproduction of CI-owned lanes.
Command taxonomy
- Use
lint:*for non-mutating static checks. - Use
format:*or an explicit fixer suffix for mutating cleanup. - Use
validate:*for non-mutating aggregates composed only of locally safe checks. - Use
test:*for locally safe deterministic or component tests. - Use
ci:*for CI-owned or otherwise non-default validation lanes, including eval-framework execution and documentation Playwright E2E.
The ci:* prefix communicates ownership and default agent behavior. It does not block direct local execution and requires no marker, wrapper, or opt-in flag.
Selection and composition
- Generic validation uses applicable local-safe commands such as
validate:local,validate:docs, or targeted checks. It does not selectci:*commands. - A task that specifically asks to run or reproduce a named CI lane may invoke its ordinary
ci:*command after its prerequisites and side effects are understood. - Keep
validate:*aggregates free ofci:*commands, fixers, generators, installers, browser actions, and interactive children. - Keep report generation noninteractive. Use a separately named
:openor:uicommand for browser or interactive behavior. - Do not restore removed
eval:*,lint:all,lint:docs-site,docs:test:e2e*, or nestedtest:e2e*compatibility aliases.
Package and workflow changes
- Coordinate a breaking package-script rename with every owning workflow consumer in the same change set.
- Preserve workflow change detection, gates, arguments, outputs, artifacts, summaries, permissions, and failure behavior when changing only an entry-point name.
- Keep agent-conformance suite orchestration and its
workflow_callinvocation unchanged unless a separate requirement justifies a package entry point. - Use existing repository syntax, workflow, and source checks plus hosted CI evidence. Do not add a command-policy test subsystem or dedicated policy job solely for this taxonomy.
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 · 43 lines · 674 tokens per session scan A bb01947b863c
hve-core ci-owned-validation.instructions.md is an instructions file published in the GitHub repository microsoft/hve-core (1,411 stars, last pushed today), licensed MIT. It adds 674 tokens to every session, about $0.0034 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
devopness CLAUDE.md
Instructions for devopness/devopness, a project described as: Devopness: AI DevOps on your cloud. Deploy apps, infra and CI/CD. Any cloud and any stack, one MCP. Deterministic API, opinionated and fully configurable. No cloud credentials in AI chats. Free plan.
kubevirt-tekton-tasks AGENTS.md
Instructions for kubevirt/kubevirt-tekton-tasks, covering kubevirt tekton tasks - project guide, jira task management, documentation, project structure and key relationships.
foundry-local cpp-ci-test-policy.instructions.md
Use when adding a new test fixture, modality, or model dependency to the C++ integration test suite, or when debugging unexpected GTESTSKIP messages in CI.
docker-zoneminder CLAUDE.md
Instructions for jantman/docker-zoneminder, covering claude.md, project overview, build and test, ci/cd and architecture.
Powershell-Copilot-Standards cicd.instructions.md
Sets up comprehensive CI/CD pipelines for PowerShell projects with automated testing and deployment.
local-ci CLAUDE.md
Claude Code instructions for redwoodjs/local-ci, covering local ci — agent instructions, rules, ci and code.