What is setup-cantrips-loop?

A setup guide for configuring a repository's coding workflow, including where durable decisions and past problem-solving notes are stored and which storage system is used.

Use it to create or update docs/agents/cantrips-loop.md and choose knowledge stores such as architecture decisions or lessons learned.

It makes the workflow's shared memory and storage choices explicit, so later tasks know where to read and save information.

setup-cantrips-loop — Skill for Claude Code and Codex by toverux: A setup guide for configuring a repository's coding workflow…

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/toverux/cantrips/setup-cantrips-loop

Any agent

npx skills add toverux/cantrips --skill setup-cantrips-loop

Clone the repo

git clone --depth 1 https://github.com/toverux/cantrips

Made for: Claude Code, Codex.

Or install cantrips, the plugin that ships this one along with the rest of its 25 skills, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/toverux/cantrips/setup-cantrips-loop.svg)](https://agentmods.dev/skills/toverux/cantrips/setup-cantrips-loop)

Your own site

<a href="https://agentmods.dev/skills/toverux/cantrips/setup-cantrips-loop"><img src="https://agentmods.dev/badge/skills/toverux/cantrips/setup-cantrips-loop.svg" alt="Measured on agentmods" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 932 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.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.00932
Opus 5	$0.00016	$0.00466
Sonnet 5	$0.00007	$0.00186
Haiku 4.5	$0.00003	$0.00093

Measured 5d ago against content hash 3bba945ca052, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

setup-cantrips-loop 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 5d 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.

skills/setup-cantrips-loop/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configure how this repo runs the cantrips loop: which opt-in knowledge stores are enabled, and which backend the six storage verbs translate to. The result is one prose doc, docs/agents/cantrips-loop.md, that storage-touching skills read in place of the plugin defaults (defaults.md).

Process

Read docs/agents/cantrips-loop.md if it exists. An existing doc makes this run an edit: summarize the current configuration, ask what the user wants to change, and carry every unrevisited answer forward unchanged.
Explain each opt-in knowledge store's role in plain words, then ask which to enable:
- docs/adr/ holds durable decisions with supersession chains — an outdated record names the record that replaced it, so decisions have history instead of silent drift. Written only through /compound's user gate; read back by /spec as the repo's decision memory.
- docs/solutions/ holds problem-shaped learnings — root cause, the gotcha, what didn't work — so the next session that hits the same problem starts from the answer.
Ask which backend seed translates the six storage verbs (the verbs and their meaning: defaults.md):
- Local markdown — the default made explicit: the verb translations in defaults.md. Ask where the artifacts live: gitignored .scratch/<feature>/ (the default — disposable working material, deleted by the human when the feature closes) or a committed path such as docs/specs/ for repos whose specs should travel with branches, worktrees, and pull requests. For a gitignored location, add the entry to .gitignore in this run, so the doc can state a fact instead of leaving every later write a chore.
- GitHub — the gh CLI: publish the spec as a GitHub issue holding the spec body; publish the tickets as one issue each, each linking its parent spec issue, blocking edges via native issue links; fetch the spec or a ticket with gh issue view; annotate the spec as an issue comment, which appends and carries its own timestamp; resolve the ticket as an issue close with a completion comment.
- Freeform — the user describes their tracker workflow in a paragraph; record that paragraph as prose and derive each verb's translation from it, asking about any verb the paragraph leaves uncovered.
Every seed holds the contract invariants in defaults.md: an annotation appends without overwriting what is there, stays time-ordered, and governs over the body it revises; a published ticket is traceable to its parent spec. When a derived translation would break one, say so and ask the user for one that holds.
Write docs/agents/cantrips-loop.md as this repo's phrasebook: a skill arrives holding a verb and leaves holding the path or command it means here. Whatever a skill still needs has to be in it. Fill the scaffold:

Read the full file on GitHub · 66 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago First seen · 66 lines · 33 tokens per session scan A 3bba945ca052

Subscribe to this mod's changes

setup-cantrips-loop is a skill published in the GitHub repository toverux/cantrips (2 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 932 once invoked, about $0.0002 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.

Code review agent-skills ai-agents claude-code claude-plugins codex-cli

git-workflow

This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…

Galaxy-Dawn/claude-scholar · 64 tokens

daily-paper-generator

Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.

Galaxy-Dawn/claude-scholar · 47 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.