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.
git clone --depth 1 https://github.com/OriginTrail/dkgWrote 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/rules/origintrail/dkg/dkg-annotate)<a href="https://agentmods.dev/rules/origintrail/dkg/dkg-annotate"><img src="https://agentmods.dev/badge/rules/origintrail/dkg/dkg-annotate/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/rules/origintrail/dkg/dkg-annotate"><img src="https://agentmods.dev/badge/rules/origintrail/dkg/dkg-annotate.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 | $0.02909 | $0.02909 |
| Opus 5.5 | $0.01164 | $0.01164 |
| Sonnet 5.5 | $0.00582 | $0.00582 |
| Haiku 4.5 | $0.00291 | $0.00291 |
Grade A, and why
dkg-annotate 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DKG annotation protocol (V10)
This repository is bound to a DKG V10 context graph (dkg-code-project). Use the dkg MCP server to keep the graph rich and convergent. The full canonical instructions live in AGENTS.md; this file is the Cursor-specific mirror.
Session context — read this every turn
Your incoming prompt is prefixed with a block injected by packages/mcp-dkg/hooks/inject-session-context.mjs:
<dkg-session-context>
<session-id>{sessionKey}</session-id>
<next-turn-index>{N}</next-turn-index>
<turn-uri>urn:dkg:chat:session:{sessionKey}#turn:{N}</turn-uri>
<agent-uri>{your agent URI}</agent-uri>
</dkg-session-context>
Parse it once and hold <turn-uri> + <agent-uri> in working memory. The capture hook at packages/mcp-dkg/hooks/capture-chat.mjs will write chat:Turn at exactly this URI after your response, so any <turn-uri> chat:proposes <X> edge you author during the turn JOINs cleanly once the post-response write lands.
If the block is missing, fall back: annotations still stand on dcterms:created + prov:wasAttributedTo even without the turn-URI edge.
(V9 sourced the session id from a session-start additionalContext payload. That path is retired in V10 — use the <dkg-session-context> block instead.)
Hook ordering is documented in the installed .cursor/hooks.json — capture-chat runs first (stashes prompt + writes state file with pendingTurnIndex), inject-session-context runs second (reads state, prepends block), inject-inbox runs third (prepends its own notice on top). Don't re-order without understanding the dependencies.
After every substantive turn
Author one per-turn assertion. Over-eagerness is not a failure mode; under-coverage is. Skip only one-line acknowledgements.
The V9 sugared dkg_annotate_turn is gone — V10 uses an explicit three-step write (create → write → share):
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 · 167 lines · 2,909 tokens per session scan A 2c32d0c8799b
dkg-annotate is a cursor rule published in the GitHub repository OriginTrail/dkg (141 stars, last pushed today), licensed Apache-2.0. It adds 2,909 tokens to every session, about $0.0116 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 2026-08-30.
Other cursor rules, from other repositories
cursor-rules
You have access to a persistent cross-session memory via the memory MCP server. Knowledge survives between sessions and is shared across agents working on the same project.
memento-conventions
Memento OS — reasoning artifact conventions for persistent AI memory.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.