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/specgit 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 | $0.00016 | $0.00266 |
| Opus 5 | $0.00008 | $0.00133 |
| Sonnet 5 | $0.00003 | $0.00053 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
spec 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
Write the SPEC. Four sections, no more:
- Ask — what was asked for, in the asker's own words. This is what the finished work gets checked against, and it is what keeps the build from drifting into something fancier than was wanted.
- Behavior — what success looks like, concretely: given these inputs, the system does this. Include the edges: 0, 1, empty, max, and error.
- Files — what to create or change, one line each, naming the existing pattern each one mirrors. List the downstream callers you'll update in the same pass; nothing deferred.
- Done — the exact commands to run and the output that means success. Not "tests pass" — the command and the expected result, including at least one end-to-end check.
Then review it before building — /spec-audit. Resolve anything the design left vague now: a SPEC that says "whatever config that other thing uses" is a guess wearing a spec's clothes.
Stop after the SPEC. The build happens in a fresh chat, so the context that grew attached to the plan is not the one that judges the result.
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 · 15 lines · 16 tokens per session scan A aef0d2deed8a
spec is a command published in the GitHub repository Ashkaan/contextium (32 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 266 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).