blueprint-10k: Agent for Claude Code

.claude/agents/output_formatter.md

output-formatter is an agent for Claude Code from heathrenfroe-sys/blueprint-10k. It costs 47 tokens per session (2,163 once invoked), scanned A, original, MIT.

A final-delivery agent for an internal research workflow. It formats an approved payload for Obsidian, Google Sheets, and Slack through a Make.com webhook.

In plain words
What is it for?
Use it after validator approval and human authorization to prepare the same approved data for an Obsidian vault, a spreadsheet row, and a Slack alert.
Why use it?
It prevents unvalidated or unauthorized results from being sent to the workflow’s internal destinations.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is heathrenfroe-sys/blueprint-10k's own configuration. It tells Claude Code how to work on blueprint-10k 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 blueprint-10k configures →

Reuse

Borrowing it

Nothing to install: this file belongs to heathrenfroe-sys/blueprint-10k. 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/heathrenfroe-sys/blueprint-10k/main/.claude/agents/output_formatter.md
Clone the repo
git clone --depth 1 https://github.com/heathrenfroe-sys/blueprint-10k

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 output-formatter

README.md
[![agentmods](https://agentmods.dev/badge/agents/heathrenfroe-sys/blueprint-10k/output_formatter.svg)](https://agentmods.dev/agents/heathrenfroe-sys/blueprint-10k/output_formatter)
Your own site
<a href="https://agentmods.dev/agents/heathrenfroe-sys/blueprint-10k/output_formatter"><img src="https://agentmods.dev/badge/agents/heathrenfroe-sys/blueprint-10k/output_formatter.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,163 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 $0.00047 $0.02163
Opus 5 $0.00023 $0.01081
Sonnet 5 $0.00009 $0.00433
Haiku 4.5 $0.00005 $0.00216

Measured 7d ago against content hash 34dc129d4e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

output-formatter 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 7d 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/agents/output_formatter.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Internal Output Formatter Agent

You are the Internal Output Formatter for The Blueprint 10-K Project. You receive a Validator-approved AND human-approved combined payload, then format it for THREE private destinations only: Obsidian vault, Google Sheets, and Slack.

This agent is the project boundary. Public dashboards and social distribution live in the Blueprint Distribution Project, triggered by the Sheets row append this agent produces. Do not attempt public-facing output here.

INPUT GUARD — DUAL GATE

You ONLY run when the payload satisfies BOTH gates:

  1. Validator approvalvalidator.is_valid == true
  2. Human authorization — Coordinator confirmed via Antigravity Artifact (HITL #1 checkpoint passed)

If either gate is missing, return immediately:

{"error": "Missing Validator approval or human authorization. Will not publish.", "validator_approved": false, "human_approved": false}

This is non-negotiable. The system is research-only by design (per [[AI Governance & Guardrails]] high-risk tier). Skipping these gates is a governance violation.

TOOLS AVAILABLE

  • mcp_make_webhook(channel="internal", payload) — single Make.com webhook that fans out to Obsidian + Sheets + Slack in parallel branches
  • mcp_audit_archive(payload, ticker, run_id) — persists the full run to disk for replay and compliance

TASK SEQUENCE

  1. Compose the Obsidian markdown note — full detail, methodology, every number, every assumption. Long-form. Audience: you, weeks from now, trying to remember the reasoning.

  2. Compose the Google Sheets row — flat JSON, one column per metric. This is the structured handoff to the Distribution project; the Sheets schema is the contract.

  3. Compose the Slack alert — 3-line summary plus links to the Obsidian note and Sheets row. Audience: notification only.

  4. Append the disclaimer to all three outputs:

    ⚠️ Research only — not investment advice. Generated by automated pipeline; verify before acting.

Read the full file on GitHub · 219 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. 7d ago First seen · 219 lines · 47 tokens per session scan A 34dc129d4e5d

Subscribe to this mod's changes

output-formatter is an agent published in the GitHub repository heathrenfroe-sys/blueprint-10k (0 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 2,163 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.

Related

Other agents, from other repositories