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.
git clone --depth 1 https://github.com/aahlijia/dekkoWrote 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/commands/aahlijia/dekko/sanity)<a href="https://agentmods.dev/commands/aahlijia/dekko/sanity"><img src="https://agentmods.dev/badge/commands/aahlijia/dekko/sanity/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/aahlijia/dekko/sanity"><img src="https://agentmods.dev/badge/commands/aahlijia/dekko/sanity.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00020 | $0.00322 |
| Opus 5.5 | $0.00008 | $0.00129 |
| Sonnet 5.5 | $0.00004 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
sanity 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 26d 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
Sanity check
!dekko sanity $ARGUMENTS
Your task
The report above was generated programmatically by the tool above — do NOT re-derive any of it yourself, and do not re-grep the repo by hand.
- Relay the match/dekko-only/grep-only buckets to the user.
- For any grep-only hit, relay the named
causeverbatim — do not invent a different explanation. - If everything matched (
clean: no grep-only misses), say so plainly; this is a spot check, not a verdict that something is wrong. - In
--unused NAMEmode the report is reference evidence for a symboldekko unusedflagged dead, each hit tagged by shape (spread/typeof/subscript/call/other). Any evidence means "not safe to delete on dekko's word alone" — relay it as such. - In
--allmode the report is a repo-wide triage summary: relay the cause histogram and the symbols with unexplained misses, and offer/sanity <symbol>on any of them for the full per-bucket detail.
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.
- 26d ago Changed · +3 lines 25d6ec77fba1
- 1mo ago Changed · +4 lines 068e38b4394a
- 1mo ago First seen · 22 lines · 20 tokens per session scan A 7eab4f8494a0
sanity is a command published in the GitHub repository aahlijia/dekko (6 stars, last pushed 7d ago), licensed MIT. It adds 20 tokens to every session and 322 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
bug-plan-creator
Deep bug investigation with architectural fix plan generation - works with any executor (loop or swarm).
quick-fix
Implement→review subagent loop with no planning phase, for a fix whose cause is known and whose shape is obvious, however many files it touches. No spec, no worktree, no docs or signals at the end; one audit. Routes to /subagent-diagnose on an unknown cause and to /atomic-plan on an open approach or contract choice.
debug
Systematic debugging with hypotheses and evidence gathering.
simplify-transform
Apply verified simplifications with user approval. Part of simplify- family.
dead-code-report
Generate dead code findings report with implementation plan. Part of dead-code- family.
simplify-verify
Verify simplification candidates pass all gates. Part of simplify- family.