Borrowing it
Nothing to install: this file belongs to glory-rs/glory. 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/glory-rs/glory/main/AGENTS.mdgit clone --depth 1 https://github.com/glory-rs/gloryWrote 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/glory-rs/glory/agents-md)<a href="https://agentmods.dev/instructions/glory-rs/glory/agents-md"><img src="https://agentmods.dev/badge/instructions/glory-rs/glory/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/glory-rs/glory/agents-md"><img src="https://agentmods.dev/badge/instructions/glory-rs/glory/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 | $0.16898 | $0.16898 |
| Opus 5.5 | $0.06759 | $0.06759 |
| Sonnet 5.5 | $0.03380 | $0.03380 |
| Haiku 4.5 | $0.01690 | $0.01690 |
Grade A, and why
glory 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 today.
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 — 1,097 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
The public value/Cage/Bond input wrapper is named Vary; use the enum and its
new name directly, without retaining a compatibility alias for the former name.
List naming is Each / each(...) / XML <Each>. ui::Each and
display::Each export the same Widget and source-generic controller. Use
each(source).key(key).children(factory) for Vec/Cage/Bond/Vary, or
each(keyed_list).children(factory) with existing member identities. DSL Each
uses the same key/children/seed contract. No index-key fallback, old arity aliases,
each_seed function or built-in For alias. See
docs/v2-unified-each-2026-10-29.md. Keep keyed rows non-Clone and zero-mirror;
vector rows retain reactive value/index handles and seed mode omits their cost.
For the completed keyed/content API and retained performance changes, read
docs/v2-display-completion-results-2026-10-29.md. Consecutive display moves
snapshot selection once and reset at other commands/packet boundaries. Keep
focus/selection, failure-prefix and GC acceptance. Removing the instance's
BindingId list regressed controlled table-clear measurements and was reverted;
do not infer speed from fewer records or allocations alone.
User-directed v2 display model (2026-10-28)
The user has explicitly revised the v2 direction: HTML/CSS is the standard
display contract; raw HTML elements and Glory's higher-level widgets are
different layers. Follow docs/v2-html-template-runtime-architecture-2026-10-28.md
for this new design and its pinned Dioxus 0.7.10 source comparison.
An XML-like DSL should emit shared display templates and dynamic slots. A raw
<button> must not implicitly instantiate a Glory Button widget or enter a
complete per-element UI/Mapper semantic Memory. Keep Cage/Bond/Vary; retain
instance/root/range, dynamic target, event/ref and necessary control state.
Physical DOM/layout/AX nodes still exist. Native targets align with the
HTML/CSS model through the document engine, with explicit verified support.
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.
- today Changed · -8 lines · -161 tokens per session 9abc510355a4
- yesterday Changed · +1 lines · +14 tokens per session b2683f9a58a7
- 4d ago Changed · +13 lines · +197 tokens per session 5ef51910e655
- 6d ago Changed · +2 lines · +50 tokens per session 71dfee067216
- 7d ago Changed · +20 lines · +393 tokens per session bb7acd06fa03
- 8d ago Changed · +16 lines · +124 tokens per session 7295bf0caba5
- 9d ago Changed · +141 lines · +2,257 tokens per session f922b65ea406
- 10d ago Changed · +159 lines · +2,472 tokens per session fa2409cb473a
- 11d ago Changed · +11 lines · +212 tokens per session 2b26ad330193
- 13d ago First seen · 742 lines · 11,340 tokens per session scan A 86109b715447
glory AGENTS.md is an instructions file published in the GitHub repository glory-rs/glory (43 stars, last pushed yesterday), licensed Apache-2.0. It adds 16,898 tokens to every session, about $0.0676 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.
glory AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| glory AGENTS.mdglory-rs/glory | Instructions file | 43 | yesterday | Apache-2.0 | A | 16,898 | 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 | yesterday | 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 |