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 rules/hmakt99/akf/cursorrulesgit clone --depth 1 https://github.com/HMAKT99/AKFWhat 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 | $0.00193 | $0.00193 |
| Opus 5 | $0.00097 | $0.00097 |
| Sonnet 5 | $0.00039 | $0.00039 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
cursorrules 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.
What it actually says
AKF — Agent Knowledge Format
When you create or modify files in this project, stamp them with AKF trust metadata:
akf stamp <file> --agent cursor --evidence "<evidence>"
When you complete a task involving commits:
akf stamp <file> --agent cursor --evidence "<summary>"
Before modifying existing files, check for trust metadata:
akf read <file>
Classification
confidentialfor finance/secret/internal pathspublicfor README, docs, examplesinternal(default) for everything else
Key commands
akf stamp— stamp trust metadataakf read— read metadataakf embed— embed into DOCX/PDF/imagesakf scan— security scanakf audit— compliance audit
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 · 30 lines · 193 tokens per session scan A 5bfb066547e9
cursorrules is a cursor rule published in the GitHub repository HMAKT99/AKF (15 stars, last pushed 1mo ago), licensed MIT. It adds 193 tokens to every session, about $0.0010 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 cursor rules, from other repositories
project
Canonical trace format and verifier for agent execution attestation.
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
ehs-ims-conventions
EHS IMS app — RBAC, data layer, tRPC, migrations, AI boundaries.
backend-python
Cursor rule "backend-python" from coeusyk/inference-x, covering backend python rules, stack assumptions, code style, fastapi conventions and schema conventions.
cursorrules
When the user asks about nist rmf, use nist-rmf-ai-mcp tools: assessriskprofile, mapaiimpact, generateriskcontrols, crosswalktoeuaiact, createriskreport.
api-tester
Expert API testing specialist focused on comprehensive API validation, performance testing, and quality assurance across all systems and third-party integrations.