Borrowing it
Nothing to install: this file belongs to ericlitman/open-pstack. 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/ericlitman/open-pstack/main/AGENTS.mdgit clone --depth 1 https://github.com/ericlitman/open-pstackWrote 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/ericlitman/open-pstack/agents-md)<a href="https://agentmods.dev/instructions/ericlitman/open-pstack/agents-md"><img src="https://agentmods.dev/badge/instructions/ericlitman/open-pstack/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/ericlitman/open-pstack/agents-md"><img src="https://agentmods.dev/badge/instructions/ericlitman/open-pstack/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 | $0.00821 | $0.00821 |
| Opus 5.5 | $0.00328 | $0.00328 |
| Sonnet 5.5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
open-pstack 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 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.
What it actually says
open-pstack
Track all durable work in this repository's GitHub Issues. Do not create a parallel Linear queue. Build a ticket that comes from a waived review finding only after that failure has been seen in real use; until then the ticket records the finding and stays unscheduled. Read UPSTREAM.md before changing upstream-derived content.
Cursor's cursor/plugins/pstack tree is the content upstream. Keep one shared skill tree for Claude Code and Codex; adapt harness primitives at the existing mapping boundaries instead of forking skills or adding compatibility layers. The parent harness resolves provider routing once. Children do not detect or reroute themselves.
Code this repository owns explains itself. UPSTREAM.md, CHANGES.md and NOTICE.md say which files are local adaptations or additions. Upstream-derived files keep upstream's comments, so later syncs stay clean. In owned code, a comment stays only if it is a legal or license header, an explanation of behaviour forced by a vendor, platform or protocol we cannot change, a formatter directive, a doc comment that defines a public API contract, or an issue or RFC link for a constraint that code cannot express. When owned code would surprise a reader, reshape it (rename, extract, add a type) instead of explaining it. Encode a "must not change" constraint as a type, test or lint, then delete its comment. Suppress a lint or type error only when its rule is wrong, pedantic or style-only; otherwise fix the cause. pstack's no-comments skill applies this rule.
Before opening a pull request, run the Bun tests, strict typecheck, static invariants, and plugin validation.
Nothing merges, tags, releases, or rolls out until the exact candidate is installed and the changed behavior passes a live test from the real user surface in every affected harness. Unit tests, validators, source inspection, and self-reports do not satisfy this gate. The record is the live-gate commit status on that exact head, which links an evidence comment naming the installed version, surface, action, and observed result. Mergify does not queue a pull request without it. A pull request may be ready for review before its live test, but every new head, including a queue-created head, needs its own.
For Open Pstack PRs, use the shared repository-local .claude/skills/verify-open-pstack/ skill (Codex: .agents/skills/verify-open-pstack). Verifier-changing PRs run from a checkout of their reviewed candidate head, with the publisher revision equal to the candidate SHA; all other PRs run from trusted main. Record the publisher revision separately from the candidate SHA. Reuse the operator's existing logins without credential source flags, extra logins, or credential reading/copying. Claude uses normal operator config with session-only --plugin-dir <exact-head checkout>/plugins/pstack --settings '{"enabledPlugins":{"pstack@open-pstack":false}}'. Codex installs the exact-head candidate in a run-owned CODEX_HOME, with auth.json symlinked to the operator's ${CODEX_HOME:-$HOME/.codex}/auth.json; absent file-based auth fails closed. Removing the run home removes only the symlink, never its target. Setup alone snapshots real ${CLAUDE_CONFIG_DIR:-$HOME/.claude}/pstack-models.md and CLAUDE.md, restores their exact bytes or original absence afterwards, and verifies restoration before any publication; restoration failure publishes nothing. Preserve private mode-0700 raw evidence through merge. Publication is one structured evidence comment plus exact-SHA live-gate; no credential parsing, token registration, or exact-secret comment checks. No PR-body, ready/draft, reversal, or compensation writes, publisher-code attestation, or OS filesystem-denial claims are permitted. Builders do not publish the gate, queue, or merge.
Do not add an implicit runtime timeout or a weaker-model fallback.
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 Changed · +2 lines · +190 tokens per session 84e48d79fcd4
- 4d ago Changed · +33 tokens per session 42aef80b439a
- 13d ago Changed · +2 lines · +384 tokens per session abcf0e63feed
- 1mo ago First seen · 12 lines · 214 tokens per session scan A 5e98bcfe9703
open-pstack AGENTS.md is an instructions file published in the GitHub repository ericlitman/open-pstack (427 stars, last pushed yesterday), licensed MIT. It adds 821 tokens to every session, about $0.0033 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 2026-08-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.