propose

A review workflow for drafting a record of an important project decision before saving it in Kauri, a decision database. It checks for similar records, selects tags, and asks a person to approve the draft.

In plain words
What is it for?
Use it when choosing a library, architecture, convention, or approach, or when resolving a trade-off. It prepares the decision’s reasoning, alternatives, constraints, related files, and status for approval.
Why use it?
It prevents minor, duplicated, or poorly worded decisions from filling the project record. Human review keeps the stored decision aligned with what the team actually chose.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/mhashim6/kauri/propose
Any agent
npx skills add mhashim6/kauri --skill propose
Clone the repo
git clone --depth 1 https://github.com/mhashim6/kauri

Made for: Claude Code, Codex.

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 741 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00119 $0.00741
Opus 5 $0.00060 $0.00370
Sonnet 5 $0.00024 $0.00148
Haiku 4.5 $0.00012 $0.00074

Measured 2d ago against content hash ef86685ad81c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

propose 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 2d 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.

plugins/claude-code/skills/propose/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Propose a Decision

Draft a decision record and present it for human approval before writing it to the database. This is the quality gate that prevents low-value or poorly-worded records from accumulating.

Steps

  1. Understand the context: Based on $ARGUMENTS and the conversation so far, identify what decision was made, why, and what alternatives were considered.

  2. Check for duplicates: Run kauri_query --text "$ARGUMENTS" to see if a similar decision already exists. If it does, ask whether to supersede it or skip recording.

  3. Check the taxonomy: Run kauri_taxonomy_list to see available tags. Pick the most fitting ones.

  4. Draft the record: Present the following to the user for review:

    Title: [short, scannable — what was decided]
    Body:
      [What was decided and why]
      [What alternatives were considered]
      [Key constraints or trade-offs]
    Tags: [tag1, tag2]
    Files: [any associated file paths]
    Links: [IDs of related decisions, if any]
    Pin: [yes/no — only if this is a critical rule the agent must always see]
    Status: [active or draft if still tentative]
    
  5. Ask for approval: Present the draft and ask:

    • "Record this decision?" (proceed)
    • "Edit something?" (revise and re-present)
    • "Skip" (don't record)
  6. Record if approved: Call kauri_record with the approved values. If superseding, include --supersedes <id>.

Quality guidelines

A good decision record:

  • Title: One sentence, starts with a verb or states the choice clearly. Good: "Use JWT with 15-minute refresh tokens". Bad: "Auth stuff".
  • Body: Explains WHY, not just WHAT. Includes the trade-off or constraint that drove the choice.
  • Tags: 1-3 tags from the taxonomy. Don't force-fit — if nothing matches, propose a new tag and explain why.
  • Files: Only files directly governed by this decision. Don't list every file that touches the feature.
  • Pin: Reserve for critical rules (security constraints, hard boundaries). Most decisions should NOT be pinned.

Read the full file on GitHub · 72 lines

Changes

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.

  1. 2d ago First seen · 72 lines · 119 tokens per session scan A ef86685ad81c

Subscribe to this mod's changes

propose is a skill published in the GitHub repository mhashim6/kauri (5 stars, last pushed 4mo ago), licensed MIT. It adds 119 tokens to every session and 741 once invoked, about $0.0006 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 2026-08-31.