Borrowing it
Nothing to install: this file belongs to manavmishra/ZeroSlop. 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/manavmishra/ZeroSlop/main/CLAUDE.mdgit clone --depth 1 https://github.com/manavmishra/ZeroSlopWrote 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/manavmishra/zeroslop/claude-md)<a href="https://agentmods.dev/instructions/manavmishra/zeroslop/claude-md"><img src="https://agentmods.dev/badge/instructions/manavmishra/zeroslop/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/manavmishra/zeroslop/claude-md"><img src="https://agentmods.dev/badge/instructions/manavmishra/zeroslop/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 | $0.01297 | $0.01297 |
| Opus 5.5 | $0.00519 | $0.00519 |
| Sonnet 5.5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
ZeroSlop 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 1mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
Development coordination
AGENTS.md remains the canonical repository contract. Preserve its runtime privacy, distribution, validation, versioning, and release requirements. These instructions add development housekeeping; they do not put Asana access into the packaged skill or change how the skill processes a user's writing.
Track authorized development automatically
When the user authorizes implementation, a fix, tests, refactoring, documentation, or release work for Zero Slop, the coordinator must invoke a bounded Asana housekeeping subagent to maintain the corresponding delivery record. The user should be able to request the work without managing cards. If the harness cannot create subagents, the coordinator performs the same role in a separate bounded pass and states that honestly.
Questions, investigation, status, and review-only requests are read-only unless the user explicitly asks to record or update them. A status-only session must not flush pending writes. These instructions run during active authorized sessions; they install no skill, daemon, scheduler, or Asana Rule.
Use the approved delivery-coordinator skill when available, and give independent
candidate reviews to delivery-reviewer in a separate run. The housekeeping role
below remains required if those skills are unavailable. Do not ask the user to
maintain cards. Skill installation is separate from authentication and scheduling.
Resolve the record and use only free features
- Prefer the authorized Asana connector and existing private local configuration. Resolve the exact Zero Slop — Delivery project and its workspace. If the target is ambiguous, ask one concise question before any mutation.
- If the connector is unavailable, the housekeeping agent may use already-authorized Chrome UI access. It must not extract browser credentials, cookies, tokens, or passwords or create a new account connection without authority.
- Use only ordinary projects, tasks, subtasks, sections, descriptions, comments, links, and List/Board views. Do not use paid Rules, custom fields, native dependencies, AI Teammates, or trial-only features. Do not change billing, invite bot accounts, or add seats.
- Match a task by an existing task URL or stable packet ID first; then inspect the repository, scope, and active work before creating anything. A similar title is not sufficient proof of a match. Reuse the existing record, including work tracked earlier in the session.
- Resolve the accountable human from the existing task or authorized user context. Record agents by role and actual run ID in the description; do not represent them as human reviewers or seats.
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.
- 1mo ago First seen · 63 lines · 1,297 tokens per session scan A 70bdafe3e675
ZeroSlop CLAUDE.md is an instructions file published in the GitHub repository manavmishra/ZeroSlop (148 stars, last pushed yesterday), licensed MIT. It adds 1,297 tokens to every session, about $0.0052 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 2026-09-09.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.