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 skills/ixanadu/tiding/startupnpx skills add iXanadu/tiding --skill startupgit clone --depth 1 https://github.com/iXanadu/tidingWrote 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/skills/ixanadu/tiding/startup)<a href="https://agentmods.dev/skills/ixanadu/tiding/startup"><img src="https://agentmods.dev/badge/skills/ixanadu/tiding/startup.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 | $0.00029 | $0.02510 |
| Opus 5 | $0.00015 | $0.01255 |
| Sonnet 5 | $0.00006 | $0.00502 |
| Haiku 4.5 | $0.00003 | $0.00251 |
Grade A, and why
startup 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session startup. Follow these steps:
0. Orientation Prelude
Do both of these before any scope=project memory calls or substantive work.
0a. Do NOT re-read what is already in context. ~/.claude/CLAUDE.md (→ ~/.agents/AGENTS.md), the project CLAUDE.md, and MEMORY.md are injected into your system prompt at launch — re-catting them costs ~1k tokens each and adds nothing. Skim them in the prompt if you need to refresh a rule.
Tool schemas — one ToolSearch call, only what startup needs: memory_get, memory_search, memory_inbox, memory_status, memory_store, memory_reply, memory_ack, Monitor. Load memory_send, memory_roster, memory_take_seat, memory_resolve_thread, memory_keys later, only if a step below actually needs them.
0b. Confirm project identity. Check .engram.cfg at the repo root.
- If present: parse
project = <name>. This is the canonical user_id for allscope=projectmemory and inbox addressing. Proceed. - If absent:
- Only auto-suggest a name when CWD matches
~/projects/<name>/(one level directly underprojects/, at the repo root) AND<name>is NOT a generic deploy label (prod,dev,staging,main,trunk,current,release,live). In that case, suggest<name>and ask the user to confirm. - Otherwise (nested layouts like
~/projects/site/sub/, domain-style~/projects/site.com/dev/, server paths like/var/www/site/prod, or anything that doesn't match the clean~/projects/<name>/shape), do NOT guess — ask the user directly for the canonical project name. Do not infer from git remotes or path segments in ambiguous cases; the user decides. - Once the user confirms the name: write
.engram.cfgat the repo root containingproject = <name>. Stage it. Commit (Add .engram.cfg — canonical project identifier).
- Only auto-suggest a name when CWD matches
1. Read Handoff Note
memory_get key=startup/next scope=project — this is the handoff from the last session.
If it references other memory keys, fetch those too.
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 · 163 lines · 29 tokens per session scan A b59b514fe37a
startup is a skill published in the GitHub repository iXanadu/tiding (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 29 tokens to every session and 2,510 once invoked, about $0.0001 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 skills, from other repositories
sema-usage
Content-addressed vocabulary protocol via the sema MCP server. Use when working with shared vocabulary — searching, resolving, minting, and verifying meaning across agents and conversations.
Memory Reasoning
Visible reasoning contract for recalling, extracting, and responding with user memory context.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
memory-curation
When you have read / processed a workspace asset in this session and learned something durable about it, write a memory page so future sessions benefit. Maintain the workspace wiki's hierarchical structure as it grows.
memory
Persist and retrieve agent memory across sessions — write durable notes, read by path, recall via semantic search, list/delete, and consolidate. Use whenever the user asks to remember/forget something, when you need to look up past decisions or context, or when episodic state matters beyond the current turn. Executes…
project-context
Use PowerContext project memory and handoff tools through MCP when continuing prior work, recalling decisions, maintaining durable memory, or transferring work across tasks, sessions, or agents.