agentmods.dev

openpitch AGENTS.md

openpitch AGENTS.md is an instructions file for Codex, OpenCode from Avierovich/openpitch. It costs 4,345 tokens per session, scanned A, original, MIT.

An agent coordination log for OpenPitch, a tool that discovers and classifies information about companies and sectors from public sources. It records current project status, collaboration rules and the project's approach to source tracking and auditability.

In plain words
What is it for?
Use it before editing OpenPitch, especially for discovery, classification, documentation, tests or changes involving public-source provenance.
Why use it?
It helps coding agents understand what work is already in progress and avoid overwriting changes made by people or other agents.

Instructions file for CodexOpenCode

not rated 8 5d ago A scan 4,345 tokens original MIT
View the source file Avierovich/openpitch
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 instructions/avierovich/openpitch/agents-md
Clone the repo
git clone --depth 1 https://github.com/Avierovich/openpitch

Made for: Codex, OpenCode.

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 openpitch AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/avierovich/openpitch/agents-md.svg)](https://agentmods.dev/instructions/avierovich/openpitch/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/avierovich/openpitch/agents-md"><img src="https://agentmods.dev/badge/instructions/avierovich/openpitch/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,345 This file is loaded in full into every session.
When invoked 4,345 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.04345 $0.04345
Opus 5 $0.02173 $0.02173
Sonnet 5 $0.00869 $0.00869
Haiku 4.5 $0.00434 $0.00434

Measured 3d ago against content hash 36ec9edb4073, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openpitch AGENTS.md 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 3d 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.

AGENTS.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Coordination Log

This file is the handoff point for agentic coding tools working in this repo. Read it before editing, especially when Codex and Claude Code are both active.

Current Coordination Rules

  • Do not revert dirty working-tree changes unless Mohamed explicitly asks.
  • Treat unlisted dirty files as user/Claude Code work until proven otherwise.
  • Prefer small, source-backed documentation changes over broad rewrites.
  • No runtime code changes were made by Codex during the competitive-research/doc pass.
  • OpenPitch's trust model remains: public sources, provenance, confidence, auditability, and conservative ToS posture.

Current State (2026-06-26)

Authoritative snapshot — the dated logs below are historical and may be stale.

  • v0.1.0, functional end-to-end. 64 tests passing; ruff check . clean.
  • Two-level taxonomy: controlled main category + subcategory + free-text specialty + business summary (pipeline/classify.py VOCAB: 12 mains / 81 subs incl. science and consumer-ai). config/taxonomy.yaml is the generated overlay; openpitch classify (re)builds it.
  • Discovery: news (US + EU/gl=GB feeds) + per-sector knowledge backfill (20 sectors), public/acquired filtered out, fail-isolated against 503s. discovered.yaml ~248 candidates.
  • Reconciliation: recency stays the headline; an unconfirmed "in talks" valuation also surfaces confirmed_value; forward-looking revenue targets dropped; contradictions require independent public sources.
  • MCP: 8 read-only tools, now declaring read-only/non-destructive annotations; exposes subcategory/specialty/summary.
  • P0 (local) done: CI + release (PyPI Trusted Publishing) + Pages workflows; CONTRIBUTING/ SECURITY/CoC/CHANGELOG + issue/PR templates; extraction cache (data/cache/seen.json); metadata → Avierovich/openpitch. Pending: the GitHub/PyPI push + account config.

Codex Edits Log

2026-06-13 - Product/strategy documentation expansion

Codex added or enriched the project documentation to reflect that OpenPitch is still in development and should launch only after credible proof assets exist.

Read the full file on GitHub · 401 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. 3d ago First seen · 401 lines · 4,345 tokens per session scan A 36ec9edb4073

Subscribe to this mod's changes

openpitch AGENTS.md is an instructions file published in the GitHub repository Avierovich/openpitch (8 stars, last pushed 5d ago), licensed MIT. It adds 4,345 tokens to every session, about $0.0217 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.

aiclaudeintelligencemcpopen-datapitchbook
Related

Other instructions, from other repositories

aquascope copilot-instructions.md

Instructions for Rekin226/aquascope, covering copilot instructions for aquascope, build, test, and lint, run all tests, run a single test file and run a single test by name.

Rekin226/aquascope · 919 tokens

swiss-public-data-mcp CLAUDE.md

Instructions for malkreide/swiss-public-data-mcp, covering project conventions for claude, how verification works here, check the result, not the activity, run the check that counts, not the one you know and the ruff pin: one source per repository.

malkreide/swiss-public-data-mcp · 2,712 tokens

kpubdata AGENTS.md

Instructions for yeongseon/kpubdata, covering agents.md, 목적, 먼저 읽을 문서, 작업 원칙 and 언어 정책.

yeongseon/kpubdata · 3,535 tokens

luxembourg-mcp CLAUDE.md

Instructions for amirdaraee/luxembourg-mcp, covering claude.md, commands, hard constraint: zero dependencies, architecture and adding or changing a tool touches five places.

amirdaraee/luxembourg-mcp · 1,135 tokens

curb CLAUDE.md

Instructions for alevizio/curb, covering curb — sf street parking, block by block, what it is, stack (intentionally minimal), spatial queries (verified working) and key product decisions / constraints (don't regress these).

alevizio/curb · 6,277 tokens

sbb-opendata-mcp CLAUDE.md

Instructions for malkreide/sbb-opendata-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.

malkreide/sbb-opendata-mcp · 6,758 tokens