Borrowing it
Nothing to install: this file belongs to AhmedAlnasser2000/REZANOVA-CAS-CALCULATOR. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AhmedAlnasser2000/REZANOVA-CAS-CALCULATOR/main/AGENTS.mdgit clone --depth 1 https://github.com/AhmedAlnasser2000/REZANOVA-CAS-CALCULATORWrote 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/instructions/ahmedalnasser2000/rezanova-cas-calculator/agents-md)<a href="https://agentmods.dev/instructions/ahmedalnasser2000/rezanova-cas-calculator/agents-md"><img src="https://agentmods.dev/badge/instructions/ahmedalnasser2000/rezanova-cas-calculator/agents-md/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/instructions/ahmedalnasser2000/rezanova-cas-calculator/agents-md"><img src="https://agentmods.dev/badge/instructions/ahmedalnasser2000/rezanova-cas-calculator/agents-md.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 | $0.05546 | $0.05546 |
| Opus 5.5 | $0.02218 | $0.02218 |
| Sonnet 5.5 | $0.01109 | $0.01109 |
| Haiku 4.5 | $0.00555 | $0.00555 |
Grade A, and why
REZANOVA-CAS-CALCULATOR AGENTS.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 20d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Calcwiz Agent Policy
Authority And Read Order
AGENTS.mdis the authoritative workflow and agent-governance file for this repository.CLAUDE.mdandGEMINI.mdare compatibility stubs only; they must defer toAGENTS.mdand must not define competing policy.- Before substantial work, every agent must read in this order:
AGENTS.md.memory/PROTOCOL.md.memory/current-state.md- the active
.memory/sessions/<task-id>/...dossier when one exists
- If any workflow or memory file conflicts with
AGENTS.md, followAGENTS.mdand update the lower-priority file afterward.
Memory Policy
- After finishing any task that changes code, architecture, tooling, UX behavior, or project workflow, append a concise dated note to
.memory/journal/YYYY-MM-DD.mdbefore sending the final response. - If the task locks in a durable product or engineering decision, also append a dated bullet to
.memory/decisions.md. - If the task leaves an unresolved design or roadmap choice, append a dated bullet to
.memory/open-questions.md. - Durable memory under
.memory/is expected to be tracked in git; temporary task tracking belongs in.task_tmp/and must stay ignored. - Update
.memory/current-state.mdand the active.memory/sessions/<task-id>/...dossier whenever a meaningful task or verified gate completes. - Memory completeness is a commit gate for meaningful work: before committing code, tooling, UX, architecture, or workflow changes, either stage the required durable-memory updates or record a short explicit reason in the active session/verification note explaining why no durable memory update was required.
- Do not mark a milestone complete when
.memory/current-state.md,.memory/decisions.md, session dossier, or journal updates required by the change are missing. .memory/current-state.mdis a current operating snapshot, not an append-only milestone log. The memory-protocol validator enforces this and the gate fails if any rule is broken:- Keep it under the 500-line protocol cap and at most 14 level-2 (
##) headings. - No milestone-id headings (e.g.
## OOE-RS12,## DISPLAY-SCHEDULER-POLISH1); finished-milestone records belong in the journal,.memory/decisions.md, session dossiers, or the.memory/research/milestones/archive. - Refresh the
Last updated: YYYY-MM-DDline on every meaningful update.
- Keep it under the 500-line protocol cap and at most 14 level-2 (
- Daily current-state catch-up is mandatory: if a journal or session dossier exists for a newer date than
.memory/current-state.md,npm run test:memory-protocolfails. Before committing the first meaningful work of a new day, refresh.memory/current-state.mdso it reflects the current repo posture for that day. - When updating
.memory/current-state.md, replace or trim superseded postures in place rather than appending. When a section grows stale or the file nears the cap, move the oldest superseded content into the current month's.memory/research/milestones/current-state-milestone-archive-YYYY-MM.md(create the monthly file if absent) — never let history accumulate in the snapshot. - Keep memory updates short, factual, and human-readable. Prefer bullets.
- Do not make runtime behavior depend on
.memory/. - If
.memory/is missing, recreate the existing structure before writing notes. - Follow
.memory/PROTOCOL.mdfor the durable-memory schema, attribution fields, journal format, and handoff rules.
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.
- 20d ago Changed · +2 lines · +207 tokens per session eb23029d02a0
- 29d ago Changed · +4 lines · +489 tokens per session da58d8b0f830
- 1mo ago Changed · +6 tokens per session ee20ca3db256
- 1mo ago Changed · +56 tokens per session d7ebeef4dc63
- 1mo ago First seen · 159 lines · 4,788 tokens per session scan A c62b0284c4ad
REZANOVA-CAS-CALCULATOR AGENTS.md is an instructions file published in the GitHub repository AhmedAlnasser2000/REZANOVA-CAS-CALCULATOR (5 stars, last pushed 21d ago), licensed MIT. It adds 5,546 tokens to every session, about $0.0222 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 2026-10-02.
REZANOVA-CAS-CALCULATOR AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| REZANOVA-CAS-CALCULATOR AGENTS.mdAhmedAlnasser2000/REZANOVA-CAS-CALCULATOR | Instructions file | 5 | 21d ago | MIT | A | 5,546 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |