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/zebbern/pocmap/agents-mdgit clone --depth 1 https://github.com/zebbern/pocmapWhat 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 | $0.02364 | $0.02364 |
| Opus 5 | $0.01182 | $0.01182 |
| Sonnet 5 | $0.00473 | $0.00473 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade A, and why
pocmap 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 2d 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.
This is a copy
86% identical to claude-code-discord AGENTS.md — 24 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS GUIDELINES
- You have skills which have practices, patterns or good information for specific work
- Quality over quantity — fewer high-quality outputs over many low-quality ones and use caution over speed.
- Prefer clean architecture, verifying and using up to date information, flexibility over rigidity, flexible code/development, good dead-code & dependency hygiene (knip) if relevant, for trivial tasks, use judgment.
- TypeScript: keep imports at the top of the file (no inline imports). Switches over unions/enums must be exhaustive (
neverindefault).
It can be spawned agents for specific tasks, but don't let them run wild. Always review their output and verify it against the real code/real run before accepting it.
Presentation & UX
Build for flexible, context-aware presentation rather than fixed dimensions or one-size layouts.
- Prefer structures that adapt to the surface (Discord embeds and components, CLI/TUI output, docs, or a future web UI) instead of hard-coded widths, lengths, or one-device assumptions.
- Keep text readable across contexts: scale or truncate thoughtfully, avoid walls of unreadable output, and preserve hierarchy (title → summary → detail).
- When content must fit platform limits (e.g. Discord embed caps), truncate safely with a clear indicator rather than failing or overflowing silently.
Knowledge Freshness & Research Preferences
Do not rely solely on your internal knowledge or training data when making implementation decisions. Your memory is frequently outdated.
Before implementing anything non-trivial (especially integrations, tools, SDKs, platforms, AI agents, or architectural patterns):
- Actively look up the latest official documentation, release notes, changelogs, and recommended approaches.
- Check whether newer versions, official solutions, or better patterns already exist that would change how the task should be approached.
- Prefer using current best practices and existing tools over rebuilding something from scratch based on older knowledge.
- If there is any uncertainty about the current recommended way to do something, ask clarifying questions instead of defaulting to what you remember.
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.
- 2d ago First seen · 191 lines · 2,364 tokens per session scan A 2af3add36634
pocmap AGENTS.md is an instructions file published in the GitHub repository zebbern/pocmap (5 stars, last pushed 9d ago), licensed MIT. It adds 2,364 tokens to every session, about $0.0118 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to claude-code-discord AGENTS.md, differing in 24 lines, and is treated as a copy.
Other instructions, from other repositories
Observal AGENTS.md
AGENTS.md instructions for Observal/Observal, covering agents.md, what observal is, harness capability support, architecture at a glance and how the modularisation works.
open-agent-hub AGENTS.md
AGENTS.md instructions for guanyang/open-agent-hub, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
cvehound AGENTS.md
AGENTS.md instructions for evdenis/cvehound, covering agents.md, where to look, adding a cve rule, metadata headers are test inputs, not documentation and gotcha: a files: path that resolves nowhere is silent.
cvehound CLAUDE.md
Claude Code instructions for evdenis/cvehound, a project described as: Check linux sources dump for known CVEs.
open-agent-hub CLAUDE.md
Claude Code instructions for guanyang/open-agent-hub, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
open-agent-hub GEMINI.md
Gemini CLI instructions for guanyang/open-agent-hub, covering gemini.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.