Borrowing it
Nothing to install: this file belongs to daviseford/aos-reminders. 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/daviseford/aos-reminders/master/AGENTS.mdgit clone --depth 1 https://github.com/daviseford/aos-remindersWrote 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/daviseford/aos-reminders/agents-md)<a href="https://agentmods.dev/instructions/daviseford/aos-reminders/agents-md"><img src="https://agentmods.dev/badge/instructions/daviseford/aos-reminders/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/daviseford/aos-reminders/agents-md"><img src="https://agentmods.dev/badge/instructions/daviseford/aos-reminders/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 | $0.06417 | $0.06417 |
| Opus 5 | $0.03209 | $0.03209 |
| Sonnet 5 | $0.01283 | $0.01283 |
| Haiku 4.5 | $0.00642 | $0.00642 |
Grade A, and why
aos-reminders 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 9d 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 — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file applies to the entire repository.
CONCEPTS.md at the repo root holds the shared domain vocabulary — entities, named processes,
and the faction / Army of Renown / battle-formation hierarchy — relevant when orienting to the
codebase or discussing how army-building concepts relate. docs/solutions/ holds documented
solutions to past problems (bugs, architecture patterns, workflow learnings), organized by
category with YAML frontmatter (module, tags, problem_type) — relevant when implementing
or debugging in documented areas.
Project purpose and current state
AoS Reminders turns an Age of Sigmar army configuration into phase-ordered reminders.
This is an Age of Sigmar fourth-edition codebase:
- the browser runtime uses the canonical model under
src/aos4/ - the checked-in runtime is generated from the accepted
aos4-corpus-2026-08-28bsnapshot - importing, cloud armies, and army sharing are AoS 4-native: roster parsers in
src/importers/(official app text, Listbot text and file upload, Sigdex text, New Recruit.ros/.rosz/.json), roster resolution insrc/aos4/import/, and the Auth0-authorized cloud client insrc/api/armyApi.ts - an army document may opt into Legends units (
allowsLegends); Legends applies as an overlay on the document's rules context during selection resolution - unrecognized browser state is deleted and replaced with a schema-valid army document; it is never translated
- the 27 decoded factions that field units are selectable through one source-complete relationship
graph; the 28th row,
Endless Spells, is a Wahapedia container for universal manifestations rather than an army, and generation now offers nothing from it, soarmyFactionshas nothing left to exclude - manifestations are a category of unit rather than an army: the five universal manifestation lores
and their 18 warscrolls come off the
Endless Spellscontainer page and are offered by all 27 armies instead of by the container, through the review'suniversalFactionContentgate - the accepted corpus contains 1,296 warscrolls, 1,012 battle profiles, 5,074 abilities, 2,269 weapons, 1,493 content groups, and 20,084 live source records
- the 75 Regiments of Renown on the accepted collection pages are classified
regiment-of-renowncontent groups (reviewedregimentsOfRenowninput), offered by exactly their inclusion factions with their regiment abilities and member warscrolls linked (issue #1858) - current standard, General's Handbook 2026-27 (
Scourge of Aqshy), Spearhead, Legends, and historical rules contexts isolate parallel and retired records; the browser defaults to the current 2026-27 seasonal context - strict generation consumes every live record and separately dispositions 19,113 superseded records (the May 2026 bulk warscroll/faction-rule rows plus the seventeen index-era Ogor datasheets the July 2026 battletome rewrites replaced, issues #1850 and #1880) so none can leak into runtime
- all 1,350 extracted official battle-profile facts have an explicit disposition: 1,013 apply to runtime, 1 remains a profile-only gap, 289 remain structured references, and 47 are superseded
- the earlier candidate/cohort reports remain checked-in reconnaissance history, not current blockers
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.
- 9d ago First seen · 510 lines · 6,417 tokens per session scan A 00e67206c2d4
aos-reminders AGENTS.md is an instructions file published in the GitHub repository daviseford/aos-reminders (54 stars, last pushed 2d ago), licensed MIT. It adds 6,417 tokens to every session, about $0.0321 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.