HyperStack — Agent Provenance Graph for Verifiable AI SKILL.md skillB

HyperStack — Agent Provenance Graph for Verifiable AI from opena2a-org/hackmyagent is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add opena2a-org/hackmyagent/HyperStack — Agent Provenance Graph for Verifiable AI@git:20261009.ca74c67

Pins git:20261009.ca74c67 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
opena2a-org/hackmyagent
Path
__tests__/fixtures/skill-permissions/hyperstack/SKILL.md
Versions recorded
1
Latest version
git:20261009.ca74c67, committed Oct 9, 2026
Size
33,032 bytes
Repository stars
90
License
Apache-2.0

The Agent Provenance Graph for AI agents — the only memory layer where agents can prove what they knew, trace why they knew it, and coordinate without an LLM in the loop. Timestamped facts. Auditable decisions. Deterministic trust. Ask 'what blocks deploy?' → exact typed answer. Git-style branching. Three memory surfaces: working/semantic/episodic. Decision replay with hindsight bias detection. Conflict detection. Staleness cascade. Utility-weighted edges that self-improve from agent feedback.…

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

# HyperStack — Agent Provenance Graph for Verifiable AI

## What this does

HyperStack is the Agent Provenance Graph for AI agents. The only memory layer where agents can **prove what they knew**, **trace why they knew it**, and **coordinate without an LLM in the loop**. Typed graph memory with three distinct memory surfaces, decision replay with hindsight detection, conflict detection, staleness cascade, and full provenance on every card.

**Tagline:** Timestamped facts. Auditable decisions. Deterministic trust. Build agents you can trust at $0/operation.

**The problem it solves:**
```
# DECISIONS.md (what everyone uses today)
- 2026-02-15: Use Clerk for auth
- 2026-02-16: Migration blocks deploy
"What breaks if auth changes?" → grep → manual → fragile
```

**What you get instead:**
```
"What breaks if auth changes?"       → hs_impact use-clerk         → [auth-api, deploy-prod, billing-v2]
"What blocks deploy?"                → hs_blockers deploy-prod      → [migration-23]
"What's related to stripe?"          → hs_recommend use-stripe      → scored list
"Anything about auth?"               → hs_smart_search              → auto-routed
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add opena2a-org/hackmyagent/HyperStack — Agent Provenance Graph for Verifiable AI@sha256:e2d87aebfc6db17c

The line at the top of this page pins the label git:20261009.ca74c67, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tsju4g73vuh5fipq.svg)](https://markdownregistry.com/a/art_tsju4g73vuh5fipq)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 9, 2026.

versioncommittedcommitsizeaudit
git:20261009.ca74c67 latest2026-10-09 ca74c67 33,032 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: ignore previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (33032 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

opena2a-org/hackmyagent · 90 stars · license Apache-2.0 · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tsju4g73vuh5fipq
GET https://markdownregistry.com/api/v1/resolve?ref=opena2a-org/hackmyagent/HyperStack — Agent Provenance Graph for Verifiable AI
GET https://markdownregistry.com/api/v1/blob/e2d87aebfc6db17c6577204e027c5e7cb69c359d7e224c95f2ab67f793f6d41e

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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from opena2a-org/hackmyagent

api-key-directive SKILL.md skill
opena2a-org/hackmyagent · __tests__/fixtures/cred-harvest-prose-clause/api-key-directive/SKILL.md · House rule for how many figures one sentence of a written report may carry.
v1.0.0 · audit A · 90 stars
numbers-in-written-reports SKILL.md skill
opena2a-org/hackmyagent · __tests__/fixtures/cred-harvest-prose-clause/authoring-skill/SKILL.md · The house style for prose that carries measurements — how many figures a sentence may hold, how to pair them, and how…
v1.4.0 · audit A · 90 stars
benign-prose SKILL.md skill
opena2a-org/hackmyagent · __tests__/fixtures/cred-harvest-prose-clause/benign-prose/SKILL.md · House rule for how many figures one sentence of a written report may carry.
v1.0.0 · audit A · 90 stars
known-miss-nominal-request SKILL.md skill
opena2a-org/hackmyagent · __tests__/fixtures/cred-harvest-prose-clause/known-miss-nominal-request/SKILL.md · House rule for how many figures one sentence of a written report may carry.
v1.0.0 · audit A · 90 stars
known-miss-semicolon-list SKILL.md skill
opena2a-org/hackmyagent · __tests__/fixtures/cred-harvest-prose-clause/known-miss-semicolon-list/SKILL.md · House rule for how many figures one sentence of a written report may carry.
v1.0.0 · audit A · 90 stars
quantity-tokens-in-prose SKILL.md skill
opena2a-org/hackmyagent · __tests__/fixtures/cred-harvest-prose-clause/quantity-tokens/SKILL.md · House rule for how many figures one sentence of a written report may carry.
v1.0.0 · audit A · 90 stars
claw-mentor-mentee SKILL.md skill
opena2a-org/hackmyagent · __tests__/fixtures/skill-permissions/claw-mentor-mentee/SKILL.md · Safe OpenClaw evolution — get safety-checked compatibility reports from expert builders delivered directly to your…
git:20261009.ca74c67 · audit A · 90 stars
metaskillbase SKILL.md skill
opena2a-org/hackmyagent · __tests__/fixtures/skill-permissions/clawforge-openclaw-skill/SKILL.md · Decompose human demands into atomic meta skills using OpenClaw Skill Forge Cutter. Run standalone skills…
v1.0.0 · audit A · 90 stars
self-configuration SKILL.md skill
opena2a-org/hackmyagent · __tests__/fixtures/skill-permissions/letta-code-self-configuration/SKILL.md · Inspect or modify Letta Code's own memory, model, context window, system prompt, compaction, permissions, toolsets…
git:20261009.ca74c67 · audit A · 90 stars
doc-tools SKILL.md skill
opena2a-org/hackmyagent · test-fixtures/hma32-skill-bundle/skills/doc-tools/SKILL.md · Utilities for formatting project documentation
v1.0.0 · audit B · 90 stars
insecure-openclaw SKILL.md skill
opena2a-org/hackmyagent · test-fixtures/insecure-openclaw/SKILL.md
git:20260203.9a5e66b · audit C · 90 stars
polymarket-tracker SKILL.md skill
opena2a-org/hackmyagent · test-fixtures/insecure-openclaw/skills/malicious-skill/SKILL.md · Track prediction markets
git:20260203.9a5e66b · audit F · 90 stars

Every file in opena2a-org/hackmyagent

Browse by kind, by grade B, or by owner.