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 skills add mhashim6/kauri --skill consultgit clone --depth 1 https://github.com/mhashim6/kauriWrote 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/skills/mhashim6/kauri/consult)<a href="https://agentmods.dev/skills/mhashim6/kauri/consult"><img src="https://agentmods.dev/badge/skills/mhashim6/kauri/consult/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/skills/mhashim6/kauri/consult"><img src="https://agentmods.dev/badge/skills/mhashim6/kauri/consult.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 | $0.00037 | $0.00533 |
| Opus 5.5 | $0.00015 | $0.00213 |
| Sonnet 5.5 | $0.00007 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
consult scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Consult Existing Decisions
Before planning or implementing changes, check whether existing decisions are relevant. This prevents accidentally contradicting past choices.
Steps
-
Search by topic: Run
kauri_querywith--text "$ARGUMENTS"and--scope bothto find decisions across project and user scopes. If the argument is a file path, also search with--fileto find decisions associated with that file. -
Broaden if needed: If the text search returns nothing, try searching by related tags (use
kauri_taxonomy_listto see available tags, thenkauri_querywith--tags). -
Read the full body: For every decision that looks relevant, call
kauri_show <id>to read the complete rationale — not just the title. -
Report what you found: Before proceeding with the plan, tell the user:
- Which decisions are relevant and what they say
- Whether the proposed work is consistent with those decisions
- Whether any decisions conflict with the proposed approach
- Whether any decisions should be superseded by the new work
-
Proceed accordingly:
- Consistent: Continue with the plan, noting which decisions support it.
- Conflicts: Ask the user whether to (a) adjust the plan to respect the
decision, or (b) supersede the decision with
kauri_record --supersedes. - No relevant decisions found: Proceed normally, and consider whether the new work itself warrants a new decision record.
When to use this
- Before any architectural or design planning
- Before changing conventions, APIs, or boundaries
- Before modifying files that appear in the session-start decision index
- When the user says "let's add", "let's change", "let's refactor", or "how should we"
- When you're unsure whether a past decision covers the current topic
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.
- 1mo ago First seen · 49 lines · 37 tokens per session scan A d59a3c0e6202
consult is a skill published in the GitHub repository mhashim6/kauri (5 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 533 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 skills, from other repositories
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
post-training-strategy
A guide to choosing and planning ways to improve an AI model after its initial training. It explains when to add knowledge, teach a response format, use trial-and-error training, or use a smaller model to learn from a larger one.