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.
npx agentmods add skills/mayank-io/mstack/vedic-chartnpx skills add mayank-io/mstack --skill vedic-chartgit clone --depth 1 https://github.com/mayank-io/mstackWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00131 | $0.01126 |
| Opus 5 | $0.00066 | $0.00563 |
| Sonnet 5 | $0.00026 | $0.00225 |
| Haiku 4.5 | $0.00013 | $0.00113 |
Grade A, and why
vedic-chart 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vedic Chart Extractor
Convert a Vedic astrology chart image (a Jagannatha Hora / Parashara's Light style printout) into a structured JSON chart and ASCII North-Indian + South-Indian diagrams. A bundled script does the work end to end.
What the source images look like
The script targets the standard software printout: a North-Indian chart (left), a
South-Indian chart (right), a birth-data header, and — crucially — a longitude
table across the bottom listing each body as sign deg' min with retrograde and
Jaimini karaka markers (e.g. Su: 4 Sc 08-DK). That bottom table is the ground
truth; houses are computed from it deterministically, so the chart diagrams are
never parsed glyph-by-glyph.
A chart-only image with no bottom table still works, but bodies the table would have carried fall back to sign-only placement (no degrees).
How it works
image --(claude vision reads the longitude table)--> chart JSON --(pure renderers)--> ASCII
House placement is house = (sign_index - lagna_index) mod 12 + 1. North-Indian is
house-fixed (Lagna always top-center, signs rotate); South-Indian is sign-fixed
(Pisces/Aries/… in fixed cells, houses rotate). Both render from the same JSON.
Usage
Extraction calls the claude CLI (must be on PATH, recent enough to accept
--effort and --allowedTools). Run the bundled script:
# extract + render both ASCII styles; JSON then charts to stdout
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/chart_to_ascii.py path/to/chart.png
# write sidecars (<stem>.json + <stem>.txt) next to the image(s)
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/chart_to_ascii.py images/*.png -o images/
# render only, no vision call, from a previously extracted JSON
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/chart_to_ascii.py chart.json --emit ascii
Options: --emit {json,ascii,both} (default both), --style {north,south,both}
(default both), -o/--outdir DIR, --model MODEL (default claude-opus-4-8),
--overwrite (re-extract even if a sibling .json exists; otherwise a cached
sidecar is reused). Data goes to stdout, progress/errors to stderr, non-zero exit
on any failure.
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.
- 2d ago First seen · 89 lines · 131 tokens per session scan A 1cfbc811a42c
vedic-chart is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 7d ago), licensed MIT. It adds 131 tokens to every session and 1,126 once invoked, about $0.0007 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…