Borrowing it
Nothing to install: this file belongs to bhuiyanmobasshir94/claude-standing-orders. 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/bhuiyanmobasshir94/claude-standing-orders/main/CLAUDE.mdgit clone --depth 1 https://github.com/bhuiyanmobasshir94/claude-standing-ordersWrote 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/bhuiyanmobasshir94/claude-standing-orders/claude-md)<a href="https://agentmods.dev/instructions/bhuiyanmobasshir94/claude-standing-orders/claude-md"><img src="https://agentmods.dev/badge/instructions/bhuiyanmobasshir94/claude-standing-orders/claude-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/bhuiyanmobasshir94/claude-standing-orders/claude-md"><img src="https://agentmods.dev/badge/instructions/bhuiyanmobasshir94/claude-standing-orders/claude-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 | $0.01292 | $0.01292 |
| Opus 5 | $0.00646 | $0.00646 |
| Sonnet 5 | $0.00258 | $0.00258 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
claude-standing-orders 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 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-standing-orders
This repository is the orchestrator–worker package. user/ installs into ~/.claude/
on every machine, so a change here changes how Claude Code behaves everywhere the package
is installed — not just in this checkout.
This repo does not keep a changelog, a decision log, or agent memory
Deliberate exception to rules/session-continuity.md, which this package itself ships and
which remains correct for every other repository. The reasons are specific to this one:
- It is a distributable package, not a codebase a team works in day to day. A maintainer's session narrative would ship to everyone who clones it.
docs/DESIGN-RATIONALE.mdalready records why the package is shaped the way it is. A decision log alongside it would be a second home for the same facts.- A repository with no continuity files produces no session brief. That is
session-brief.mjsbehaving as documented, not a gap to fix.
So: do not create docs/changelogs/, docs/decisions/, or .claude/agent-memory/ here.
.gitignore already blocks the last one. Record what changed and why in the commit message.
Product references are not this repo's own usage
user/, project-template/, examples/, and INSTALL.md mention docs/changelogs/,
docs/decisions/DECISIONS.md, docs/adr/, and .claude/continuity.json throughout. Those
describe what onboarded projects do. They are the product. Removing them to make the repo
"consistent" breaks the package. When unsure whether a reference is product or this repo's
own practice, it is product — leave it.
Conventions
- Aliases, never version numbers, in agent config. Agents pin
opus/sonnet/haiku. The one exception is the Claude Code version floor, which is a real runtime dependency rather than a model choice: it lives inuser/version-floor.jsonand nowhere else.bootstrap.mjssubstitutes it intosettings.template.jsonat install time (__MIN_VERSION__),session-brief.mjswarns against it, andbootstrap.mjs doctorchecks it. Never restate the number in prose — reference the file. - No
effortfield on amodel: haikuagent. Haiku does not support effort levels; the setting is silently ignored, which asserts a guarantee the runtime never provides. - Nothing personal ships. No real names, absolute home paths, private project names, or content from a private conversation — in any file, including docs and comments.
- Hook paths are generated, not committed.
settings.template.jsoncarries__CLAUDE_HOME__;bootstrap.mjsresolves it per machine. - Observability hooks fail open.
session-brief.mjs,worker-ledger.mjs,packet-check.mjs,compact-state.mjs, andverify-reminder.mjsmust exit 0 on every path, including malformed input. There is no authorization boundary among them, and none of them may block even where the event would allow it:packet-check.mjsruns onPreToolUseand must never emitpermissionDecision: "deny", andcompact-state.mjsandverify-reminder.mjsmust never block, thoughPreCompactandStopboth permit it.verify-reminder.mjsis additionally inert unless a project opts in viaverifyCommands— it must never infer verification commands. - A hook is not verified until its real payload has been seen.
packet-check.mjsshipped reading aprompt_textfield that no Claude Code release ever sent, and every static check in this repo passed while it did nothing. Exercise a hook against a payload captured from a live run —verify-repo.mjspins the fields each one depends on for exactly this reason. Stopfires every assistant turn, not once per session. Anything hooked there scans incrementally from a saved offset and short-circuits before doing real work.- No subprocess on the session-start path.
session-brief.mjsderives the Claude Code version fromCLAUDE_CODE_EXECPATHand stays silent when it cannot.claude --versioncosts 0.26–1.5s and belongs indoctor, which the user ran on purpose.
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 · 91 lines · 1,292 tokens per session scan A 5ac2da8b0fd9
claude-standing-orders CLAUDE.md is an instructions file published in the GitHub repository bhuiyanmobasshir94/claude-standing-orders (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,292 tokens to every session, about $0.0065 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
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.