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/ixanadu/tiding/agents-mdgit clone --depth 1 https://github.com/iXanadu/tidingWrote this? Show the measurements
A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.
[](https://agentmods.dev/instructions/ixanadu/tiding/agents-md)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 | $0.01919 | $0.01919 |
| Opus 5 | $0.00959 | $0.00959 |
| Sonnet 5 | $0.00384 | $0.00384 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
tiding AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Health check: `curl http://localhost:8920/health` How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tiding
Public repository — treat anything committed here as permanent and world-readable. Use placeholders for hosts, domains, personal paths and internal names, and run
scripts/repo-hygiene-check.shbefore committing (it must reportdenylist enforced; without a local.hygiene-denylistit does not check names).
Generic semantic memory service for AI agents. FastAPI + pgvector + in-process sentence-transformers embeddings.
Sources of Truth
BACKLOG.md(repo root) — the single source of truth for OPEN work. Lean ledger, open items only, written as if public (no completed items, no vuln detail, no PII/topology/client names). Standard:docs/backlog-standard.md. READ IT EVERY SESSION.- Journal → engram memory (
scope=project): completed-item stories (fix/<id>), decisions (decision/*), lessons (lesson/*, scope=shared), long item detail (backlog/<ID>), open-vuln repro detail (vuln/<ID>until shipped). Memory-first; no state files.
The Backlog — READ EVERY SESSION, SWEEP EVERY WRAPUP
BACKLOG.md is force-loaded each run. Triage every defect on discovery: BLOCKING (breaks build / wrong-or-harmful output / destroys data → fix now) vs DEGRADING (still does its job → add a ledger line and keep moving). If it's not in the ledger, it's not tracked. When idle, pull the top OPEN item. Done = delete the line in the same commit as the fix — never accumulate FIXED sections; the story goes to memory. Repo hygiene: scripts/repo-hygiene-check.sh must stay clean (assume-public doctrine).
Project Structure
server/— FastAPI app (config, db, embeddings, auth, routers, services)server/services/— memory_service.py (all CRUD), principal_service.py (identity/auth)server/routers/— memory.py, admin.py, principals.pyserver/auth.py— PrincipalAuthMiddleware (two-mode: enrichment vs enforcement)server/dependencies.py— auth helpers (get_current_principal, require_admin, check_namespace_access)
integrations/homeassistant/— Pyscript client + Blueprint for HA voice assistantsintegrations/claude-code/— MCP bridge (engram-mcp) for Claude Codescripts/— install/start/restart/uninstall + migrate_ha_memorylaunchd/+systemd/— Service templatestests/— 400+ server tests (API, auth, admin, embeddings, e2e, memory_service, principal_service, permissions, bootstrap, seats/registry, inbox/wake, channels-rip); plus 340+ MCP-bridge tests underintegrations/claude-code/tests/docs/— Getting-started, messaging, multi-provider, backlog standard, design/ (architecture, credentials);docs/archive/holds superseded-era docs
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 · 99 lines · 1,919 tokens per session scan A 73e6b8e62301
tiding AGENTS.md is an instructions file published in the GitHub repository iXanadu/tiding (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,919 tokens to every session, about $0.0096 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
tubecli AGENTS.md
Instructions for tubecreate/tubecli, covering contributor & ai assistant guidelines, attribution — must be preserved and scope.
OpenExecutive CLAUDE.md
Claude Code instructions for SenteLabsAI/OpenExecutive, covering open executive — claude code context, project overview, repository layout, key commands and python setup.
AgentCore AGENTS.md
Instructions for Lawofall/AgentCore, covering agents.md, 先读哪里, docs 与 rules and 开发 / 测试（最短）.
e-commerce-agents CLAUDE.md
Instructions for nitin27may/e-commerce-agents, covering claude.md, what this is, working artifacts location, key commands and start everything from scratch (one command).
sema AGENTS.md
Instructions for emergent-wisdom/sema, covering repository agent guide, development workflow, vocabulary changes, vocabulary review and the improvement loop, per pattern.
hybro AGENTS.md
Instructions for hybroai/hybro, covering repository guidelines, scope, project structure & module organization, build, test, and development commands and coding style & naming conventions.