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/npcworkspace-cmyk/eric-task-master/agents-mdgit clone --depth 1 https://github.com/npcworkspace-cmyk/eric-task-masterWrote 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/npcworkspace-cmyk/eric-task-master/agents-md)<a href="https://agentmods.dev/instructions/npcworkspace-cmyk/eric-task-master/agents-md"><img src="https://agentmods.dev/badge/instructions/npcworkspace-cmyk/eric-task-master/agents-md.svg" alt="Measured on agentmods" 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 | $0.00214 | $0.00214 |
| Opus 5 | $0.00107 | $0.00107 |
| Sonnet 5 | $0.00043 | $0.00043 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
eric-task-master 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 3d 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.
What it actually says
Agent rules
Read ARCHITECTURE.md before changing code.
- Keep browser execution pure Playwright. Do not add CDP, Puppeteer, Chrome debugger, or a second browser-control plane.
- Keep Profile and task management in the same-origin Web Dashboard. User-installed extensions may run only in persistent Profiles when the Owner enables them. The sole action-coordination surface is the bounded cooperative Worker FIFO; it is not extension authentication. Do not add extension installation/inventory payloads, a second extension control plane, session transfer, or extension-state copying.
- Keep site-specific behavior in task modules or specialized Skills.
- Preserve Profile exclusive leases, task heartbeat/progress, diagnostic screenshots, and deterministic cleanup.
- Never expose cookies, tokens, authentication headers, or profile paths in public API responses or logs.
- Increment the version for every delivered iteration with
npm run version:bump -- patch|minor|major. - Run
npm run checkbefore delivery. This gate includes static boundaries, all tests with real Chromium, and the full acceptance suite.
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.
- 3d ago First seen · 12 lines · 214 tokens per session scan A 26e2da7ef018
eric-task-master AGENTS.md is an instructions file published in the GitHub repository npcworkspace-cmyk/eric-task-master (1 stars, last pushed 3d ago), licensed MIT. It adds 214 tokens to every session, about $0.0011 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
browser-harness AGENTS.md
AGENTS.md instructions for browser-use/browser-harness, covering code priorities, commands, doctor — install/daemon/browser state, unit tests (no live browser) and security.
browser-harness CLAUDE.md
Claude Code instructions for browser-use/browser-harness, a project described as: Browser Harness | Self-healing harness that enables LLMs to complete any task.
BrowserMesh AGENTS.md
AGENTS.md instructions for scrollDynasty/BrowserMesh, covering browsermesh — autonomous implementation agent instructions, 1. responsibility boundary, 2. core architecture, 3. core runtime invariants and explicit addressing.
BrowserMesh CLAUDE.md
Claude Code instructions for scrollDynasty/BrowserMesh, covering browsermesh, responsibility boundary, architecture invariants, source of truth and commands.
AgenticCrawler AGENTS.md
Instructions for Mingye-Lu/AgenticCrawler, covering agents.md, project, commands, non-interactive provider setup (agent/ci use) and exit codes: 0=ok 1=error 2=usage/config 3=not-configured.
tsaagan AGENTS.md
Instructions for michaelolmos/tsaagan, covering agents.md — how to drive tsaagan, pick the lightest layer that does the job, the loop (every browser step), safety doctrine (non-negotiable) and memory.