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/ozgurkarahan/ai-agent-memory/close-weekgit clone --depth 1 https://github.com/ozgurkarahan/ai-agent-memoryWrote 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/ozgurkarahan/ai-agent-memory/close-week)<a href="https://agentmods.dev/instructions/ozgurkarahan/ai-agent-memory/close-week"><img src="https://agentmods.dev/badge/instructions/ozgurkarahan/ai-agent-memory/close-week.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 | $0.00456 | $0.00456 |
| Opus 5 | $0.00228 | $0.00228 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
ai-agent-memory close-week.instructions.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.
What it actually says
Close Week
When the user says "close week", "Friday review", or "/close-week":
Resolve the memory root
Resolve WIKI_ROOT using memory/schema.md, then schema.md, then the pointer in AGENT.md. Stop with the missing path if none contains both schema.md and index.md. All paths below are relative to WIKI_ROOT.
- Resolve active ISO week (TZ Europe/Paris) →
ops/weekly/2026-W{NN}.md. - Aggregate
ops/activity.jsonlevents for that week — group bytopic, counttouches, listdays, findlast. Sort by touches desc. - Regenerate the activity block between the sentinels (wholesale replace):
Wikilink rule:<!-- BEGIN GENERATED ACTIVITY --> ...table... <!-- END GENERATED ACTIVITY -->[[topic]]only ifresolved: true; else plain text +*(unresolved)*. - Optional connected-source pull for "what shipped" — sent mail, collaboration decisions, meetings, or modified files. Skip when no work-data tool is available.
- Draft Friday review sections: Wins · Misses · Lessons → graduate (propose ingest targets, don't auto-run) · Seed for W+1 (top-3 carry-over per topic).
- Freeze:
status: closed, bumpdate_updated, appendlog.mdentry:... CLOSE-WEEK | 2026-W{NN} | events: N | topics: [...] | wins: N | lessons-promoted: N. - (Optional) Seed W+1 — create
ops/weekly/{next}.mdskeleton.
Anti-patterns:
- ❌ Do not edit outside the sentinels on regenerate.
- ❌ Do not auto-
/ingestlessons — explicit user confirm per item. - ❌ Do not reopen a closed week. Late events → current open week with a note.
- ❌
ops/activity.jsonlis append-only — never delete events at close.
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 · 32 lines · 456 tokens per session scan A 0ddde21f0b5f
ai-agent-memory close-week.instructions.md is an instructions file published in the GitHub repository ozgurkarahan/ai-agent-memory (8 stars, last pushed 1mo ago), licensed MIT. It adds 456 tokens to every session, about $0.0023 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
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
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.