compound-refresh

compound-refresh is a skill for Claude Code, Codex from toverux/cantrips. It costs 32 tokens per session (1,536 once invoked), scanned A, original, MIT.

A review workflow that checks the project's AGENTS.md instructions and, when enabled, its docs/solutions knowledge files against the current code. It removes guidance that is outdated, duplicated, or contradicted.

In plain words
What is it for?
Use it to audit knowledge documents, verify referenced files and snippets, find overlap or contradictions, and prune information that no longer helps.
Why use it?
It keeps stored instructions and past solutions aligned with how the code currently works. This reduces the chance that future agents follow obsolete paths, names, or fixes.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the cantrips plugin — 25 skills, 3 agents shipped together

Good fit Use it to audit knowledge documents, verify referenced files and snippets, find overlap or contradictions, and prune information that no longer helps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toverux/cantrips/compound-refresh
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 toverux/cantrips --skill compound-refresh
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, 3 agents.

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 compound-refresh

README.md
[![agentmods](https://agentmods.dev/badge/skills/toverux/cantrips/compound-refresh/github.svg)](https://agentmods.dev/skills/toverux/cantrips/compound-refresh)
Your own site
<a href="https://agentmods.dev/skills/toverux/cantrips/compound-refresh"><img src="https://agentmods.dev/badge/skills/toverux/cantrips/compound-refresh/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 compound-refresh

Your own site · 80×15
<a href="https://agentmods.dev/skills/toverux/cantrips/compound-refresh"><img src="https://agentmods.dev/badge/skills/toverux/cantrips/compound-refresh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,536 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 $0.00032 $0.01536
Opus 5.5 $0.00013 $0.00614
Sonnet 5.5 $0.00006 $0.00307
Haiku 4.5 $0.00003 $0.00154

Measured 13d ago against content hash 74c031ced389, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compound-refresh 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 13d 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/compound-refresh/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit the knowledge stores against the current codebase and prune what no longer earns its place. Two stores: the project's AGENTS.md, always, and docs/solutions/ when the loop config enables it. The loop config is docs/agents/cantrips-loop.md; when that doc is absent, the solutions store is off. The opt-in docs/adr/ store stays out of scope by design — supersession is its own hygiene mechanism. Every change is gated on the user, or on a deputy engaged in their place.

Scope

An argument narrows the sweep to matching docs/solutions/ docs — try it as a filename, then a frontmatter area/tags value, then a content keyword. No argument → every doc plus AGENTS.md. AGENTS.md is in scope on every run: when the solutions store is off, or no doc matches the argument, say so in one line and audit AGENTS.md alone.

Audit docs/solutions/

The format contract is ../compound/solutions-format.md. For each doc in scope, cross-check its claims against the current code — cited paths and names still exist, the fix still matches how the code works today, snippets reflect the current implementation — and against its sibling docs for overlap and contradiction. Verdict per file:

  • Keep — still accurate and useful. No edit: reported as reviewed, zero churn.
  • Update — the problem is still real but the doc drifted, from moved paths and renamed names up to a fix the current code now contradicts. On approval: evidence-backed in-place edits; on a contradicted fix, rewrite the doc to the current truth and present it as the rewrite it is.
  • Consolidate — two docs overlap so heavily a maintainer must read both to get the truth. On approval: merge unique content into the canonical (broadest, most current) doc, delete the other.
  • Delete — both the implementation and the problem domain are gone, or the doc is fully redundant. On approval: delete the file — git history is the archive.

Judgment rules:

  • Match docs to reality, never the reverse. When code and doc disagree, the doc changes; whether the code should have changed is outside this skill.
  • Age alone is clean. A two-year-old doc that still matches the code is a Keep; age only prompts a closer look.
  • Unverifiable is not false. A claim the repo cannot corroborate — a schema fact, an operational practice, an environment behavior — is not thereby wrong; repos rarely witness their own operations. Never delete content, or strip it during a merge, solely because no in-repo artifact confirms it. Act only on contradiction, where the code demonstrably does otherwise; an unverifiable-but-plausible claim is a Keep with the verification gap noted in the report.
  • Redundant needs a quoted artifact. A doc is fully redundant only when a named in-repo artifact states its reasoning in its own text — a test, a code comment, AGENTS.md, a sibling doc — and the verdict quotes it; topical overlap is not coverage. Reasoning only partly recoverable → Update instead: cut what the artifact states, point at it in one line, and keep the measured facts, cross-file invariants, and rejected alternatives nothing else records.
  • Shared code is not shared problem. Two accurate docs on different sub-problems stay separate even when they cite the same file.
  • Contradictions between docs outrank staleness — they actively mislead. Resolve them first, via Consolidate or Update.
  • Before a Delete, check the problem domain and the inbound links. Implementation gone but the domain still alive (the app still handles what the doc addresses) → Update to the current truth instead. Other markdown citing the doc substantively (relying on it for content not stated inline) → Update instead; decorative "see also" citations are cleaned up alongside the delete.
  • Skip cosmetic churn. Typos and wording polish are edits without evidence value.

Read the full file on GitHub · 81 lines

Files

What ships with it

1 file 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.

  1. 13d ago Changed · +2 lines 74c031ced389
  2. 1mo ago Changed · +3 lines 8f554c43cca5
  3. 1mo ago Changed 279a0a7a7eda
  4. 1mo ago First seen · 76 lines · 32 tokens per session scan A 1cb5f685cc42

Subscribe to this mod's changes

compound-refresh is a skill published in the GitHub repository toverux/cantrips (3 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,536 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.

Related

Other skills, from other repositories

context-canvas-checkpoint

Maintain an optional session task map and explicit retrievable references in Context Canvas Codex. Use when navigation or long-context offload would materially help with goals, decisions, progress, dependencies, blockers, next steps, exploration summaries, large textual tool results, or selective historical…

phenomenoner/Chatgpt-Codex-App-Plus · 88 tokens

aitask-note

Send a durable note to an existing aitask — context that task needs which is not itself work. Use when you learn something a task that already exists depends on, such as a stale assumption in its body, a wider blast radius, or a decision that changes its approach.

beyondeye/aitasks · 59 tokens

yesloop

Autonomous task loop — analyze, plan, execute, verify, review, finish. Runs as visible TUI agent in git worktree. Use when user says "yesloop", "loop", "run it autonomously".

carsteneu/yesmem · 48 tokens

security-review

Use when reviewing code for vulnerabilities, checking diffs for injection/XSS/auth/crypto issues. Invokes on code changes (.go/.py/.js/.ts/.java/.rs/.php/.rb), not docs-only diffs.

carsteneu/yesmem · 50 tokens

cortex-memory

Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.

Fozikio/cortex-engine · 36 tokens

git-pr-review

A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.

huangwb8/skills · 76 tokens