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 instructions/remedy92/boxaide/agents-mdgit clone --depth 1 https://github.com/Remedy92/boxaideWrote 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/remedy92/boxaide/agents-md)<a href="https://agentmods.dev/instructions/remedy92/boxaide/agents-md"><img src="https://agentmods.dev/badge/instructions/remedy92/boxaide/agents-md.svg" alt="Measured on agentmods" 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 | $0.01426 | $0.01426 |
| Opus 5 | $0.00713 | $0.00713 |
| Sonnet 5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
boxaide 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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
Ship
A merge to master is not a download. The install button is GitHub releases/latest. CI does not publish a release.
The repo is boxaide.
After a land, from the main checkout (~/Projects/boxaide), never a worktree:
./scripts/ship_status.sh
./scripts/ship.sh
ship.sh is the only publisher. A hook on master only reminds.
The release note is the commit subject
ship.sh builds the release body from the commit subjects since the last tag,
minus merges, minus its own "Cut 0.2.24", minus the (#84) a squash-merge
appends. Boxaide then shows that body under "What is new", flattened to plain
text by src/update/notes.ts — GitHub hands the updater rendered HTML, so
nothing may be printed raw.
So a commit subject on master is user-facing copy. Write it in the present
tense, saying what the app now does, in words somebody who does not read this
repo would understand. "Archive mail, and give an agent's sweep one undo", not
"refactor sweep handler". Nothing else is written for the release; there is no
second place to fix it later.
That rule is checked, by scripts/lib/check-subject.mjs and nothing else. It
is called three times:
- CI, on the pull request title (
.github/workflows/release-note.yml). A squash-merge writes that title tomasterword for word, so this is the only gate that runs before the words are user-facing. It re-runs when the title is edited. ship.sh, over the notes it computed, before the bump and the notarise. It catches a commit pushed straight tomaster, which CI never sees.- The
commit-msghook, for a local commit, wherenpm run ship:hookshas been run. Weakest of the three: it never sees a pull request title.
The first of those depends on a GitHub setting that is not in this repo, so it cannot be reviewed and will not show up in a diff:
gh api repos/Remedy92/boxaide --jq .squash_merge_commit_title # PR_TITLE
It must read PR_TITLE. On the default, COMMIT_OR_PR_TITLE, a pull request
holding exactly one commit is squashed under that commit's subject instead of
the title, and CI only ever read the title. The check would still be green and
the words would still be unread. Restore it with:
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.
- 4d ago First seen · 111 lines · 1,426 tokens per session scan A 24f7f364f8a7
boxaide AGENTS.md is an instructions file published in the GitHub repository Remedy92/boxaide (0 stars, last pushed yesterday), licensed MIT. It adds 1,426 tokens to every session, about $0.0071 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 2026-08-31.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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 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.