kit-precedent

kit-precedent is a skill for Claude Code from dwarvesf/dwarves-kit. It costs 95 tokens per session (456 once invoked), scanned A, original, MIT.

A read-only lookup guide for finding existing tools, scripts, skills, scheduled jobs, or memory notes before proposing a new one. It searches the project's precedent inventory and reports either a matching item or no result.

In plain words
What is it for?
It helps check whether a proposed capability already exists and look up past decisions, specifications, or retrospectives before planning new work.
Why use it?
It reduces duplicate work and helps place an improvement in an existing tool instead of creating another overlapping one.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the kit plugin — 16 skills, 39 commands, 31 agents, 9 hooks shipped together

Good fit It helps check whether a proposed capability already exists and look up past decisions, specifications, or retrospectives before planning new work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dwarvesf/dwarves-kit/kit-precedent
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.

Any agent
npx skills add dwarvesf/dwarves-kit --skill kit-precedent
Clone the repo
git clone --depth 1 https://github.com/dwarvesf/dwarves-kit

Made for: Claude Code.

Or install kit, the plugin that ships this one along with the rest of its 16 skills, 39 commands, 31 agents, 9 hooks.

Wrote 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.

agentmods badge for kit-precedent

README.md
[![agentmods](https://agentmods.dev/badge/skills/dwarvesf/dwarves-kit/kit-precedent/github.svg)](https://agentmods.dev/skills/dwarvesf/dwarves-kit/kit-precedent)
Your own site
<a href="https://agentmods.dev/skills/dwarvesf/dwarves-kit/kit-precedent"><img src="https://agentmods.dev/badge/skills/dwarvesf/dwarves-kit/kit-precedent/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.

agentmods 80×15 button for kit-precedent

Your own site · 80×15
<a href="https://agentmods.dev/skills/dwarvesf/dwarves-kit/kit-precedent"><img src="https://agentmods.dev/badge/skills/dwarvesf/dwarves-kit/kit-precedent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00095 $0.00456
Opus 5.5 $0.00038 $0.00182
Sonnet 5.5 $0.00019 $0.00091
Haiku 4.5 $0.00010 $0.00046

Measured 2d ago against content hash b5f2b0787b76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kit-precedent 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.

integrations/hermes/skills/kit-precedent/SKILL.md · 42 lines

What it actually says

kit-precedent

The kit owns the search. This skill only says when to run it.

 about to propose something new  -->  precedent find --surface inventory --quiet <words>
                                          |
                          hit  -->  quote the hit's one-line summary, propose enhancing that thing
                          none -->  say "no precedent found" and continue

When to use

Before you propose a NEW tool, script, skill, cron job, or memory note. Also when asked whether something already exists.

How to answer

  1. Run ~/.claude/dwarves-kit/bin/precedent find --surface inventory --quiet <two to five words naming the idea>.
  2. If a hit comes back, quote its summary line as printed and say the work belongs in that thing, in its own repo.
  3. If nothing comes back, say so in one line. Do not claim certainty beyond the search you ran.
  4. For past decisions, specs, or retros, use --surface records instead of inventory.
  5. When the idea is a name (board), query that name alone: an item with exactly that name prints first, in an exact section. precedent index writes the full page by cluster, layer, and kind.

Never

  • Never search other repos by hand to answer this. The command is the lookup.
  • Never create the new thing in the same turn because the search came back empty. Report, then wait for the operator.
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 Changed · +1 lines b5f2b0787b76
  2. 20d ago First seen · 41 lines · 95 tokens per session scan A 64cbc407b768

Subscribe to this mod's changes

kit-precedent is a skill published in the GitHub repository dwarvesf/dwarves-kit (12 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 456 once invoked, about $0.0004 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 2026-10-07.