openpitch: Skill for Claude Code

.claude/skills/run-openpitch/SKILL.md

run-openpitch is a skill for Claude Code, Codex from Avierovich/openpitch. It costs 58 tokens per session (624 once invoked), scanned B, original, MIT.

A runbook for operating the OpenPitch data pipeline and dashboard. OpenPitch collects company information, can transcribe and extract information with language models, and publishes the resulting dataset.

In plain words
What is it for?
Use it to seed the dataset, run live or offline refreshes, process selected companies, serve the MCP server, build the dashboard, and test OpenPitch.
Why use it?
It provides repeatable commands for preparing data, refreshing it, serving the system, building the dashboard, and running tests.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions Claude Code; mentions Codex.

This is Avierovich/openpitch's own configuration. It tells Claude Code and Codex how to work on openpitch 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 openpitch configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Avierovich/openpitch. 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/Avierovich/openpitch/main/.claude/skills/run-openpitch/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Avierovich/openpitch

Made for: Claude Code, Codex.

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 run-openpitch

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/avierovich/openpitch/run-openpitch"><img src="https://agentmods.dev/badge/skills/avierovich/openpitch/run-openpitch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 624 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00058 $0.00624
Opus 5 $0.00029 $0.00312
Sonnet 5 $0.00012 $0.00125
Haiku 4.5 $0.00006 $0.00062

Measured 9d ago against content hash 69d00d28392e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

run-openpitch scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`[mcp_servers.openpitch]` to `~/.codex/config.toml`.
.claude/skills/run-openpitch/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run OpenPitch

Prescriptive runbook for operating the OpenPitch pipeline. The git-tracked data/ tree is the database; everything is reproducible and zero-cost.

0. Environment (once)

python -m venv .venv && source .venv/bin/activate
pip install -e ".[pipeline]"        # core + Gemini provider

Secrets go in a gitignored .env (never commit it):

  • LLM_API_KEY — free Gemini key (extraction). Without it, only seed works.
  • GROQ_API_KEY — free Groq key (hosted Whisper transcription). Optional.
  • OPENPITCH_SEC_USER_AGENTOpenPitch/0.1 [email protected] (EDGAR fair-access).

1. Build the dataset (offline, no key)

openpitch seed          # reconcile committed seed claims -> data/ (idempotent same-day)

Produces data/companies/*.json, history, events, digest, universe, index.

2. Live refresh (needs LLM key + network)

openpitch run                       # all watchlist companies
openpitch run --companies 5         # first 5 (quota-safe for a test)
openpitch run --ids openai,mistral  # specific companies
openpitch run --offline             # falls back to seed

Stages: collect → transcribe → extract (batched) → derive → reconcile → publish. Fail-isolated per company. Scoring is global (ranks the full committed set).

3. Build the dashboard + A2A card

openpitch build-dashboard           # -> dashboard/dist/ (open index.html)

4. Serve the MCP server (read-only, no LLM, no key)

openpitch-mcp                       # stdio MCP server over committed data

Register it: claude mcp add openpitch -- openpitch-mcp (Claude Code) or add [mcp_servers.openpitch] to ~/.codex/config.toml.

5. Test & verify

PYTHONPATH=src pytest tests/ -q     # full suite
openpitch quality-report            # data-quality gaps -> data/quality/report.md

Guardrails

  • Never commit .env or real secrets (DATA-POLICY).
  • Prefer published transcripts; transcription stores only short phrases, never full transcripts.
  • Respect source ToS / robots; official APIs and RSS first.
  • Data is probabilistic public-source intelligence — every figure keeps its source + confidence.

Read the full file on GitHub · 68 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. 9d ago First seen · 68 lines · 58 tokens per session scan B 69d00d28392e

Subscribe to this mod's changes

run-openpitch is a skill published in the GitHub repository Avierovich/openpitch (8 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 624 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

ai-news-intelligence

AI News Intelligence pipeline for ForThePeople.in. Use this skill when building, debugging, or extending the automated news analysis system that reads Indian news, extracts civic data, and updates the district dashboard. Triggers: 'AI intelligence', 'news pipeline', 'Gemini analyzer', 'auto-update from news'…

jayanthmb14/forthepeople · 106 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens