Borrowing it
Nothing to install: this file belongs to trentkm/stormlight. 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/trentkm/stormlight/main/AGENTS.mdgit clone --depth 1 https://github.com/trentkm/stormlightWrote 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/trentkm/stormlight/agents-md)<a href="https://agentmods.dev/instructions/trentkm/stormlight/agents-md"><img src="https://agentmods.dev/badge/instructions/trentkm/stormlight/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/trentkm/stormlight/agents-md"><img src="https://agentmods.dev/badge/instructions/trentkm/stormlight/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 | $0.04534 | $0.04534 |
| Opus 5.5 | $0.01814 | $0.01814 |
| Sonnet 5.5 | $0.00907 | $0.00907 |
| Haiku 4.5 | $0.00453 | $0.00453 |
Grade A, and why
stormlight 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 2mo 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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on Stormlight
Guidance for coding agents and contributors. Design rationale lives in README.md (the Design section) and docs/; this file covers how work gets done.
Philosophy
Stormlight is pre-release. There are no users to break yet, so build things the right way the first time:
- No half measures, no backwards-compatibility shims, no quick hacks layered on wrong designs. When a fix reveals a design flaw, fix the design, not the symptom.
- Breaking refactors are welcome.
- Verify real behavior empirically (run the thing, capture the bytes) rather than building on assumptions about how a provider or terminal behaves.
Tracking work
- Outstanding work is tracked as GitHub issues. File follow-ups with
gh issue create, reference issues in commits, and close them (Fixes #Norgh issue close) when the work lands. - Commit and push completed work as it lands; don't let it pile up.
- Commits carry no AI attribution — no
Co-Authored-Bytrailers.
Work in a worktree
Every task starts in its own git worktree, cut from the freshly fetched
origin/main — never in the primary checkout, and never from local main:
git fetch origin
git worktree add -b <branch> --no-track .claude/worktrees/<branch> origin/main
Fetch every time. Branching off local main inherits whatever that checkout
last saw, which is stale the moment anyone else's PR merges; origin/main
after a fetch is the real tip. --no-track is not optional — a branch created
from a remote-tracking ref otherwise adopts origin/main as its upstream, and
a later git push either refuses or aims at the wrong branch. With it, the
branch starts upstreamless and git push -u origin <branch> does the right
thing.
While the work is in flight, keep the branch stacked on current main. Fetch and rebase before you push:
git fetch origin && git rebase origin/main
That keeps the PR a linear diff against the tip rather than a merge knot, and surfaces conflicts while the change is still yours to reshape.
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.
- 2mo ago First seen · 381 lines · 4,534 tokens per session scan A 32ce15e48df1
stormlight AGENTS.md is an instructions file published in the GitHub repository trentkm/stormlight (5 stars, last pushed 29d ago), licensed MIT. It adds 4,534 tokens to every session, about $0.0181 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 2026-08-31.
stormlight AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stormlight AGENTS.mdtrentkm/stormlight | Instructions file | 5 | 29d ago | MIT | A | 4,534 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |