finance-automation-portfolio: Skill for Claude Code

.claude/skills/loops/SKILL.md

loops is a skill for Claude Code from sophonfinance-wq/finance-automation-portfolio. It costs 46 tokens per session (361 once invoked), scanned A, original, MIT.

A set of five self-healing workflows that check data, find errors, repair them from an authoritative source, and check again before deciding whether to pass, flag, or stop.

In plain words
What is it for?
Use it to run demonstrations of all five workflows, compare their gate policies, or explain how the observe-and-recheck architecture works.
Why use it?
It helps keep automated corrections from silently changing facts or numbers. Each workflow applies a different review rule, including human approval or quarantine when needed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sophonfinance-wq/finance-automation-portfolio's own configuration. It tells Claude Code how to work on finance-automation-portfolio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything finance-automation-portfolio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sophonfinance-wq/finance-automation-portfolio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sophonfinance-wq/finance-automation-portfolio/main/.claude/skills/loops/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sophonfinance-wq/finance-automation-portfolio

Made for: Claude Code.

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 loops

README.md
[![agentmods](https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/loops/github.svg)](https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/loops)
Your own site
<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/loops"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/loops/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 loops

Your own site · 80×15
<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/loops"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/loops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 361 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 $0.00046 $0.00361
Opus 5 $0.00023 $0.00180
Sonnet 5 $0.00009 $0.00072
Haiku 4.5 $0.00005 $0.00036

Measured 11d ago against content hash ea9583d50aa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

loops 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 11d 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.

.claude/skills/loops/SKILL.md · 19 lines

What it actually says

The Self-Healing Loop Family

Five loops, one architecture: observe -> detect -> remediate -> re-verify -> gate -> repeat. Sensor = the engine's own control harness. Authority = deterministic re-derivation from the seeded source of record. The loop never invents a number.

Engine Command (from its folder) Gate policy Exit
Close python -m close_engine.loop --demo autonomous + quarantine (AUTO-POSTED/PARTIAL/HALTED) HALTED=1
Tax surplus python -m surplus_engine.loop --demo human-gated (PASS/FLAG/FAIL) FAIL=1
Recon python -m recon_engine.loop --demo materiality (PASS/FLAG/FAIL) FAIL=1
Knowledge brain python -m brain_engine.loop --demo verbatim-or-refuse (CLEAN/REMEDIATED/ESCALATED) ESCALATED=3
Triangulate python -m triangulate.loop --sample adversarial arithmetic vs judgment (CLEAN/AUTO-CLEARED/ESCALATED) non-PASS=1

Full sweep: run all five demos and report each verdict line. Docs: ARCHITECTURE.md section 5a; each engine README has a loop section; assets/flows/self-healing-close-loop.svg is the CPA-readable diagram.

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. 11d ago First seen · 19 lines · 46 tokens per session scan A ea9583d50aa5

Subscribe to this mod's changes

loops is a skill published in the GitHub repository sophonfinance-wq/finance-automation-portfolio (11 stars, last pushed 15d ago), licensed MIT. It adds 46 tokens to every session and 361 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 2026-08-30.

Related

Other skills, from other repositories

browser-edge-cases

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

aden-hive/hive · 40 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens

debugging-executions

Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.

n8n-io/n8n · 48 tokens

atmos-schemas

JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.

cloudposse/atmos · 32 tokens

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

therapeutic-ifs

Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.

winstonkoh87/Athena-Public · 34 tokens