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 commands/optimeta/paideia/weakmapgit clone --depth 1 https://github.com/OPTIMETA/PAIDEIAWhat 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 | $0.00038 | $0.01199 |
| Opus 5 | $0.00019 | $0.00600 |
| Sonnet 5 | $0.00008 | $0.00240 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
weakmap 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments: $ARGUMENTS
Output language
Read INTERFACE_LANG from .course-meta (default en). All user-facing prose — chat output and the narrative portions of the report MD — must be in that language. Keep in English regardless: file paths, slash command names, pattern IDs (P1, P2…), YAML keys, tier markers (🔥🔥/🔥/🟡/⚪), the report's literal section anchors (# Weakmap — <ts>, ## Error histogram, ## Top 5 weaknesses, ## User-declared weaknesses, ## Exam-hot zones not yet drilled, ## One-line verdict) and the table column headers (Pattern/topic, Latest error type, Date, §) — downstream tools regex on these.
Purpose
Use when the user notices "I think I'm weak at this point" while studying — they record it with /weakmap <concept> and it accumulates in the report. Called without arguments, it takes a fresh snapshot from the latest error log.
Storage rules
- Report directory:
weakmap/ - File name:
weakmap/weakmap_<YYYY-MM-DD_HHmm>.md - Top heading:
# Weakmap — <YYYY-MM-DD HH:mm> - Never overwrite. Always save a new timestamped file (preserve history).
- "Latest report" = the file in
weakmap/with the most recent mtime.
Branches
Case A — no argument (fresh snapshot)
- Read
errors/log.md. Group YAML entries bypattern. - Within each pattern, keep only the entry with the most recent
date. Older errors may have already been corrected, so "current weakness snapshot" = latest only. - Cross-reference with
course-index/coverage.md's reverse map — the 🔥 exam tiers and any⚠weakflags. - (If present) the prior weakmap's "User-declared weaknesses" section is not re-included. A no-argument call is an error-log-driven re-snapshot, so user-declared stays empty in this mode.
- Write to
weakmap/weakmap_<ts>.mdin the format below and print a chat summary.
Case B — with argument (concept patch)
"Read the latest report → append the new concept to user-declared (cumulative: A, B + C) → rewrite the whole report against {A, B, C} → save under a new timestamp."
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 · 94 lines · 38 tokens per session scan A de28dbb7768f
weakmap is a command published in the GitHub repository OPTIMETA/PAIDEIA (91 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,199 once invoked, about $0.0002 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 commands, from other repositories
fieldtheory
Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…
wiki-retro
Save an atomic insight from the current task into the wiki. Creates a single markdown file that layered recall surfaces in future sessions.
publish
Publishes the portfolio: runs the link check, hands off to the content editor for any last fixes, then follows the deploy runbook.
tree-ring-capture
Capture a concise validated lesson decision warning or preference in Tree Ring Memory.
demo-command
Example slash command that wraps the demo-skill. Showcases the command kind.
luyao-character
Command "luyao-character" from wordflowlab/novel-writer, covering 塑造平凡而伟大的人物, 使用方法, 人物类型, 基础类型 and 复合类型.