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/ashkaan/contextium/projectgit clone --depth 1 https://github.com/Ashkaan/contextiumWhat 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 | $0.00015 | $0.00168 |
| Opus 5 | $0.00008 | $0.00084 |
| Sonnet 5 | $0.00003 | $0.00034 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
project 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 yesterday.
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
Run the Think move of the Contextium Loop.
- Understand what is actually being asked. If it is a real decision (architecture, a vendor, anything hard to reverse), present the options and trade-offs and wait. If it is execution, plan it and move.
- Write a lean SPEC with four sections: what was asked, what success looks like (including the 0 / 1 / empty / max / error edges), the files to touch, and the exact commands that prove it works.
- Present the SPEC and get explicit sign-off before building.
Stop here. The Do move happens in a fresh chat so a context that grew attached to the plan is not the one that judges the build.
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.
- yesterday First seen · 12 lines · 15 tokens per session scan A da43d7afe533
project is a command published in the GitHub repository Ashkaan/contextium (32 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 168 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 2026-08-30.
Other commands, from other repositories
test-tools
Test MCP NixOS Tools (project).
release
Review and publish the Release Please release PR, then verify every registry.
design-qa
Agent-driven design QA — walk the running app, judge design/UX, and drop a Comment-Mode comment on every issue (visible to the human as pins). Then read the session back and fix everything in bulk. Optional focus argument steers the pass.
best-of
Spawn N parallel code-task sub-agents in worktrees and apply the winner's diff (code/file-change tasks only).
checkpoint
Write a new link in the continuum chain summarizing decisions/changes since the last link.
dream
Roll up the last N links into a single phase-digest link; originals move to archived/ (never deleted).