Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<!-- hyperfide-owned: generated-spec v1 -->
---
description: Ion portable spec workflow (task-driven + cortex)
alwaysApply: true
---
<!-- GENERATED by cg spec render from spec/ kvx — DO NOT EDIT. -->
# Demo Spec Workflow
This file is a generated pointer. The single workflow source is `spec/workflow.kvx`; edit it and run `hyperfide spec render`, never this file.
## Active feature
`spec/demo/spec.kvx` — read its `[meta]` status, `[req.*]` acceptance criteria, and the `[task.*]` list (status + wave + requires). Work one task at a time in wave order; update `status` in the kvx as you go.
## The loop (every session)
1. Read the active spec.kvx.
2. Pick the next eligible task by wave.
3. Implement, verify, mark done.
## Where the rules are
Principles, hard rules and policies live only in `spec/workflow.kvx`: `[principle]`, `[hard_rules]`, `[status_values]`, `[memory]`. Read them there.
The line at the top of this page pins the label git:20261022.a8528d7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_4atayxzlxubuws4w
GET https://markdownregistry.com/api/v1/resolve?ref=sidiora-labs/hyperfide/tests/fixtures/specrepo/.cursor/rules/spec-workflow.mdc
GET https://markdownregistry.com/api/v1/blob/3e42d777253225b703be7cad48e65799c35ea97940754c35735e93ea74740fc6
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
sidiora-labs/hyperfide · .agents/skills/add-contributor/SKILL.md · Approve a GitHub contributor to open PRs in hyperfide/hyperfide platform, then land the allowlist change with SlopCop…
sidiora-labs/hyperfide · .agents/skills/codify-workflow/SKILL.md · Ground coding work in the local Codify graph, spec, evidence, and handoff lifecycle.
sidiora-labs/hyperfide · .agents/skills/create-verification-skill/SKILL.md · Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API…
sidiora-labs/hyperfide · .agents/skills/maintain-verification-skill/SKILL.md · Audit an existing verification skill and feature map against source and the running app, then repair proven…
sidiora-labs/hyperfide · .agents/skills/plugin-guide-maintenance/SKILL.md · Update Plugin Guide cards, fixtures, and annotations when public SDK contracts or Guide presentation change.
sidiora-labs/hyperfide · .agents/skills/test-audit/SKILL.md · Gate new or changed tests, and audit existing tests for low value, implementation coupling, duplication, and the…
sidiora-labs/hyperfide · .agents/skills/verify-hyperfide/SKILL.md · Verify HYPERFIDE user journeys in an isolated source dev app using dev-browser@next and the matching source CLI. Use…
sidiora-labs/hyperfide · examples/plugins/agent-enrichment/skills/repo-conventions/SKILL.md · Repository conventions for commits, pull requests, and tests in this example project.
sidiora-labs/hyperfide · plugins/account-pool/skills/account-pool/SKILL.md · Configure or diagnose Account Pooler accounts, authentication, quota routing, and failover through Hyperfide pool.
sidiora-labs/hyperfide · plugins/agent-annotations/skills/agent-annotations/SKILL.md · Create or edit element annotations in desktop Browser tabs, or update saved annotation comments through the plugin RPC.
tencentcloudbase/cloudbase-ai-toolkit · connectors/cloudbase-intl/skills/references/spec-workflow/SKILL.md · Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation…
tencentcloudbase/cloudbase-ai-toolkit · plugin/cloudbase-codex/skills/spec-workflow/SKILL.md · Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation…
tencentcloudbase/cloudbase-ai-toolkit · connectors/cloudbase/skills/references/spec-workflow/SKILL.md · Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation…
tencentcloudbase/cloudbase-ai-toolkit · config/source/skills/spec-workflow/SKILL.md · Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation…
tencentcloudbase/cloudbase-ai-toolkit · plugin/cloudbase/skills/spec-workflow/SKILL.md · Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation…
tencentcloudbase/cloudbase-ai-toolkit · config/.claude/skills/spec-workflow/SKILL.md · Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation…
tzachbon/smart-ralph · plugins/ralph-specum/skills/spec-workflow/SKILL.md · This skill should be used when the user asks to "build a feature", "create a spec", "start spec-driven development"…
