AGENTS.md@src/ptc_agent/agent/prompts/templatesA

AGENTS.md@src/ptc_agent/agent/prompts/templates from ginlix-ai/langalpha is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add ginlix-ai/langalpha/src/ptc_agent/agent/prompts/templates/AGENTS.md@git:20261101.3bc35f3

Pins git:20261101.3bc35f3 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
ginlix-ai/langalpha
Path
src/ptc_agent/agent/prompts/templates/AGENTS.md
Versions recorded
9
Latest version
git:20261101.3bc35f3, committed Nov 1, 2026
First version recorded
Sep 1, 2026
Size
13,290 bytes
Repository stars
2,249
License
Apache-2.0

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Prompt templates

Jinja2 sources for the PTC and subagent system prompts. Rendered by
`PromptLoader` (`../loader.py`); defaults live in `../config/prompts.yaml`.
The PTC prompt renders per role: the analyst's is the base prompt, and the
Chief of Staff's adds `components/chief_of_staff.md.j2` as a `<role>` section,
so a change there never touches a workspace's prompt or its cached prefix.
`workspace_context`, `workspace_paths`, `task_workflow` and `memory` also read
`role`: Home's `agent.md` is the Chief of Staff's notebook of what the user is
focused on and where that work lives, laid out in `<role>`, not a workspace's
index of its own work, and Home's workspace memory is how the user wants it to
work. A shared section that describes the analyst's
`agent.md` argues with `<role>`, and the model then keeps both layouts. Subagents
render these sections without `role`, so they read the analyst's wording.

Preview any surface as it renders at runtime:

```bash
uv run python scripts/utils/render_prompt.py --crawl --count-tokens
uv run python scripts/utils/render_prompt.py --subagent equity-analyst
uv run python scripts/utils/render_prompt.py --role chief_of_staff
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ginlix-ai/langalpha/src/ptc_agent/agent/prompts/templates/AGENTS.md@sha256:d328202cfbcf3261

The line at the top of this page pins the label git:20261101.3bc35f3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_3otkfyekyzrmk4o3.svg)](https://markdownregistry.com/a/art_3otkfyekyzrmk4o3)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 9 versions of this file, between Sep 1, 2026 and Nov 1, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20261101.3bc35f3 latest2026-11-01 3bc35f3 13,290 BA view · diff
git:20261028.a0973962026-10-28 a097396 12,481 BA view · diff
git:20261020.d4e7d3a2026-10-20 d4e7d3a 12,500 BA view · diff
git:20261017.0a1701a2026-10-17 0a1701a 11,917 BA view · diff
git:20261007.0d6ef742026-10-07 0d6ef74 11,977 BA view · diff
git:20261006.3a6185c2026-10-06 3a6185c 10,796 BA view · diff
git:20260930.628dfde2026-09-30 628dfde 9,851 BA view · diff
git:20260913.8fae40d2026-09-13 8fae40d 9,849 BA view · diff
git:20260901.8abca612026-09-01 8abca61 6,244 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (13290 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ginlix-ai/langalpha · 2,249 stars · license Apache-2.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3otkfyekyzrmk4o3
GET https://markdownregistry.com/api/v1/resolve?ref=ginlix-ai/langalpha/src/ptc_agent/agent/prompts/templates/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/d328202cfbcf32611957021a7224810b2d7058c0696f3ecab13c43c5506b59ed

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from ginlix-ai/langalpha

AGENTS.md AGENTS.md file
ginlix-ai/langalpha · AGENTS.md
git:20261101.1663d2c · audit A · 2,249 stars
CLAUDE.md CLAUDE.md file
ginlix-ai/langalpha · CLAUDE.md
git:20260711.40c6e92 · audit A · 2,249 stars
DESIGN.md DESIGN.md file
ginlix-ai/langalpha · DESIGN.md
git:20261108.b1945c6 · audit A · 2,249 stars
AGENTS.md@desktop AGENTS.md file
ginlix-ai/langalpha · desktop/AGENTS.md
git:20261024.46a2ed1 · audit B · 2,249 stars
web-scraping SKILL.md skill
ginlix-ai/langalpha · plugins/alternative_data/skills/web-scraping/SKILL.md · Web scraping: scrape_page / scrape_pages MCP tools for fetching pages as markdown, HTML, or text (fast HTTP, browser…
git:20260921.26f807b · audit A · 2,249 stars
x-api SKILL.md skill
ginlix-ai/langalpha · plugins/alternative_data/skills/x-api/SKILL.md · Search X (Twitter) posts, pull user profiles, fetch specific tweets, and read reply threads for sentiment, news, and…
git:20260928.de2d0b4 · audit A · 2,249 stars
chart-annotation SKILL.md skill
ginlix-ai/langalpha · plugins/langalpha_deliverables/skills/chart-annotation/SKILL.md · Extra guidance for draw_chart_annotation, which works without loading this. Covers choosing between similar variants…
git:20261005.0db6b54 · audit A · 2,249 stars
docx SKILL.md skill
ginlix-ai/langalpha · plugins/langalpha_deliverables/skills/docx/SKILL.md · Word documents a human will review and edit: build with python-docx, edit an existing file in place with tracked…
git:20260921.26f807b · audit A · 2,249 stars
html-report SKILL.md skill
ginlix-ai/langalpha · plugins/langalpha_deliverables/skills/html-report/SKILL.md · Self-contained styled HTML reports written to the task directory: PDF-exportable research documents with inline data…
git:20260921.26f807b · audit B · 2,249 stars
inline-widget SKILL.md skill
ginlix-ai/langalpha · plugins/langalpha_deliverables/skills/inline-widget/SKILL.md · Inline HTML widgets: charts, dashboards, data tables rendered directly in the chat via ShowWidget
git:20260921.26f807b · audit F · 2,249 stars
interactive-dashboard SKILL.md skill
ginlix-ai/langalpha · plugins/langalpha_deliverables/skills/interactive-dashboard/SKILL.md · Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors, served via preview URL
git:20261025.20c54f6 · audit C · 2,249 stars
pdf SKILL.md skill
ginlix-ai/langalpha · plugins/langalpha_deliverables/skills/pdf/SKILL.md · Read, fill and build PDFs: inspect structure and fonts, extract text and tables with pdfplumber and poppler, fill and…
git:20260921.26f807b · audit A · 2,249 stars

Every file in ginlix-ai/langalpha

Browse by kind, by grade A, or by owner.