Borrowing it
Nothing to install: this file belongs to tmustier/pine-of-glass. 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/tmustier/pine-of-glass/main/AGENTS.mdgit clone --depth 1 https://github.com/tmustier/pine-of-glassWrote 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/tmustier/pine-of-glass/agents-md)<a href="https://agentmods.dev/instructions/tmustier/pine-of-glass/agents-md"><img src="https://agentmods.dev/badge/instructions/tmustier/pine-of-glass/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/tmustier/pine-of-glass/agents-md"><img src="https://agentmods.dev/badge/instructions/tmustier/pine-of-glass/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 | $0.00943 | $0.00943 |
| Opus 5 | $0.00472 | $0.00472 |
| Sonnet 5 | $0.00189 | $0.00189 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
pine-of-glass 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pine-of-glass: agent notes
Three pi extensions (contextimate, traceline, cachemire) sharing one design
language. TypeScript, zero runtime dependencies, tests on node:test.
Commands
npm run link-pi # symlink the installed pi runtime into node_modules (types + contract tests); run first on a fresh clone
npm run link-extensions # symlink the extensions (as directories) into ~/.pi/agent/extensions
npm run docs:cache # regenerate Cachemire retention docs
npm run lint # coding-standard and generated-doc drift checks
npm run typecheck # tsc against the real installed pi
npm test # unit + golden + pi contract tests (zero deps, node:test)
npm run check # lint + typecheck + tests
npm run test:smoke # launches real pi in tmux with an isolated HOME (local-only)
Layout & rules
- One extension per
extensions/pi-<name>/; shared code lives inextensions/_lib: number grammar, family style (glyphs, theme-derived ink, panel headers), ANSI helpers, chat-container detection, config convention._libhas noindex.ts, so pi's extension discovery skips it. - pi resolves extension-relative imports against the symlink path, so local installs
must link the extension directories plus
_lib;npm run link-extensionsdoes exactly that. docs/design-language.mdspecifies the visual grammar all three extensions speak. Record design changes there first, then implement; when a renderer and that document disagree, one of them is wrong.- The contract suite pins every structural assumption about pi internals, so after
pi updatea quicknpm testsays exactly which seam (if any) drifted. Test design notes:docs/testing.md. - Before changing Cachemire retention, read the dated
audit.
retention.tsdrives runtime resolution and generated policy docs;cacheClock()owns clock wording. Match the exact route, model and outgoing policy. Keep minimum and maximum semantics distinct, and leave unmatched routes unknown. Runnpm run docs:cacheafter policy changes. - Goldens regenerate with
UPDATE_GOLDENS=1 npm test. Review the diff like code. Regenerate whenever rendering changes. - README screenshots regenerate with the rig in
scripts/dev/screenshots/: real pi TUI in an isolated tmux/HOME; see its README for the recipe. Thecachemirescenario makes live model calls (costs cents). - Agent coding standards live in
docs/agent-coding-standard.mdand are enforced byscripts/dev/agent-lint.mjs. Boundary uncertainty belongs at Pi, JSON, config, provider-payload, and catch seams only. Do not add genericisRecordorisObjecthelpers. Parse or refine at the edge, pass typed values inward, and document real escape hatches withSAFETY:comments.
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.
- 10d ago First seen · 68 lines · 943 tokens per session scan A 88cffec4e919
pine-of-glass AGENTS.md is an instructions file published in the GitHub repository tmustier/pine-of-glass (48 stars, last pushed yesterday), licensed MIT. It adds 943 tokens to every session, about $0.0047 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).
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 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.