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/catcam/hads/claude-mdgit clone --depth 1 https://github.com/catcam/hadsWrote 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/catcam/hads/claude-md)<a href="https://agentmods.dev/instructions/catcam/hads/claude-md"><img src="https://agentmods.dev/badge/instructions/catcam/hads/claude-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 | $0.00619 | $0.00619 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
hads 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HADS — Human-AI Document Standard
Version 1.0.0 · Open Standard · 2026-03-26 · HADS 1.0.0
AI READING INSTRUCTION
Read [SPEC] blocks for authoritative facts. SPEC.md je kompletna specifikacija.
1. Što je HADS
[SPEC] HADS je tagging konvencija za Markdown tehničku dokumentaciju. Cilj: AI modeli mogu brzo identificirati što je autoritativna činjenica vs. narativ.
Četiri taga: [SPEC] (fakti), [NOTE] (kontekst), [BUG] (poznati bugovi), [?] (neverificirano)
Svaki HADS dokument mora imati AI manifest koji govori modelu što čitati.
[NOTE] HADS ne izmišlja novi format — koristi standardni Markdown. Zero adoption friction.
2. Lokalne kopije
[SPEC]
/home/botuser/hads/ — lokalna kopija repozitorija
SPEC.md — kompletna specifikacija (ground truth)
SKILL.md — Claude Code skill za pisanje HADS dokumenata
api-reference.md — API referenca
validate.py — validator
paper.md — akademski rad
hads_paper.pdf — PDF verzija rada
GitHub: catcam/hads (public), catcam/hads-skills (public)
3. Status projekta
[SPEC]
- arXiv submission: odbijen (independent researcher, nema institucijsku afiliaciju)
- Zenodo: nije submitano
- PRs: LangChain
langchain-ai/langchain-community#593, Anthropic skills
[NOTE]
HADS rok: NLnet grant prijava bila 1.4.2026 — prošlo. Grant nije podnesen.
NLnet proposal: /home/botuser/hads-nlnet-proposal.md
4. Korištenje
[SPEC]
# Validacija HADS dokumenta
cd /home/botuser/hads
venv/bin/python3 validate.py path/to/doc.md
# GitHub sync
cd /home/botuser/hads && git pull
gh repo view catcam/hads
[SPEC] HADS skill za Claude Code (za pisanje novih HADS dokumenata):
Skill: hads
5. Benchmark
[SPEC]
/home/botuser/hads-benchmark/ — benchmark infrastruktura + hooks
- Hooks: PreCompact, Stop, PostToolUse (browsing reminder)
- Docs:
/home/botuser/hads-benchmark/
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.
- 4d ago First seen · 84 lines · 619 tokens per session scan A 545001d30808
hads CLAUDE.md is an instructions file published in the GitHub repository catcam/hads (28 stars, last pushed 1mo ago), licensed MIT. It adds 619 tokens to every session, about $0.0031 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 2026-08-30.
Other instructions, from other repositories
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).