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/implement-auditgit 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 | $0.00018 | $0.00221 |
| Opus 5 | $0.00009 | $0.00111 |
| Sonnet 5 | $0.00004 | $0.00044 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
implement-audit 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
Adversarially review the change you just built, with fresh eyes. The goal is to find what a self-satisfied author would miss.
- Re-read the SPEC, then the diff. Where do they disagree?
- Hunt for: missed edge cases (0 / 1 / empty / max / error), inconsistency with sibling code, downstream callers that now break, and silent failure modes.
- Triage each finding as must-fix, should-fix, or a nit. Fix every must-fix and should-fix whose fix is ready before you commit — the label orders the work within this round, it does not schedule it to a later session. Clear the nits in one pass at the end.
In Claude Code this runs as a fresh-context review agent. In other tools, open a clean chat, load only the SPEC and the diff, and run this review there — a context that wrote the code is the wrong one to judge it.
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 · 18 tokens per session scan A a11d9a7d2ad7
implement-audit is a command published in the GitHub repository Ashkaan/contextium (32 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 221 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).