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/mothblight-git/pyre/claude-mdgit clone --depth 1 https://github.com/MothBlight-Git/pyreWhat 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 | $0.06525 | $0.06525 |
| Opus 5 | $0.03263 | $0.03263 |
| Sonnet 5 | $0.01305 | $0.01305 |
| Haiku 4.5 | $0.00653 | $0.00653 |
Grade A, and why
pyre CLAUDE.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 yesterday.
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 — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PYRE — build spec
A frameless, transparent, always-on-top desktop grid of square paper notes. A note with a deadline burns away from its bottom edge in the last two hours. Notes can be dragged anywhere on the grid; burning ones claim the top-left unless you have moved them yourself. Everything is readable and writable by an AI agent. The whole thing runs from a single portable executable.
This document is the build contract. Read it fully before writing code.
0. Authority order
When these disagree, higher wins:
- This file — the current requirements.
reference/burn-system.css— an approved verbatim extraction of the fire rendering. Copy it in unchanged. Several gradient stops are non-obvious and were arrived at by fixing specific visual defects; reconstructing them by eye will look wrong and you will not know why.reference/note-example.html— the fidelity target. Open it in Chrome; your build must match it.reference/design-handoff.md— the design system doc. Still authoritative for type, colour, layer order, motion and copy. Superseded only where §1 below says so.reference/Pyre Rail Directions.dc.html— the full design exploration. Reference, not source.
spec/ holds tested reference implementations of the two things the design files do not cover. Copy them into src/ as indicated in each header; they are not pseudocode.
1. What changed since the design handoff
Four requirements landed after the design was approved. Each one supersedes part of it.
| # | Change | Supersedes |
|---|---|---|
| 1 | Burning starts at T−2h and maxes at due. | The 7-day heat horizon and heat = clamp01(1 − t/168). The "firelight · 5d" and "glow · 2d" stages are no longer burn stages — they become the ambient warmth band (§2.2). |
| 2 | Notes are draggable on a free grid. | "Sort: descending heat… not user-configurable in v1." |
| 3 | Burning notes take the top-left unless intentionally moved. | The pure sort. Sort now governs only unpinned notes. |
| 4 | Portable single-file package. | ~/.stickyburn/notes.json as the only data location. |
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.
- yesterday First seen · 422 lines · 6,525 tokens per session scan A f6378c0f7194
pyre CLAUDE.md is an instructions file published in the GitHub repository MothBlight-Git/pyre (0 stars, last pushed 11d ago), licensed MIT. It adds 6,525 tokens to every session, about $0.0326 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
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.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.