Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mickpletcher/AI-Skillsnpx agentmods add commands/mickpletcher/ai-skills/upgrade-astrophotography-processingWrote 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.
[](https://agentmods.dev/commands/mickpletcher/ai-skills/upgrade-astrophotography-processing)<a href="https://agentmods.dev/commands/mickpletcher/ai-skills/upgrade-astrophotography-processing"><img src="https://agentmods.dev/badge/commands/mickpletcher/ai-skills/upgrade-astrophotography-processing/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.
<a href="https://agentmods.dev/commands/mickpletcher/ai-skills/upgrade-astrophotography-processing"><img src="https://agentmods.dev/badge/commands/mickpletcher/ai-skills/upgrade-astrophotography-processing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.04859 |
| Opus 5.5 | $0.00012 | $0.01944 |
| Sonnet 5.5 | $0.00006 | $0.00972 |
| Haiku 4.5 | $0.00003 | $0.00486 |
Grade A, and why
upgrade-astrophotography-processing 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 — 586 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upgrade the astrophotography-processing skill
Act as the implementation agent for the existing Claude skill at
claude/skills/astrophotography-processing/.
Read this entire prompt before editing. Inspect the repository and current files first. Do not assume that the working tree is clean or that the skill still matches the baseline described here.
How to invoke this prompt
Run this prompt from GitHub Copilot Chat in agent mode with:
/upgrade-astrophotography-processing phase=1
Replace phase=1 with the phase to implement. If no phase is supplied, inspect the repository,
report current status, and recommend the next incomplete phase without changing files.
Implement one phase at a time unless the user explicitly requests multiple phases. At the end of each phase, run the relevant tests and report changed files, validation results, assumptions, and remaining work.
Primary objective
Turn the skill from a broad advisory router into an evidence-driven astrophotography copilot that can safely inspect datasets, produce diagnostic artifacts, recommend processing workflows, invoke approved external tools, and validate before-and-after results.
Keep Claude as the reasoning, workflow-selection, diagnosis, and quality-control layer. Reuse established astronomical processing engines rather than attempting to recreate PixInsight, Siril, Astro Pixel Processor, or DeepSkyStacker.
Required repository context
Read these files before making changes:
shared/skill-standard.mdshared/platform-organization.mdshared/naming-conventions.mdclaude/skills/astrophotography-processing/SKILL.md- every file under
claude/skills/astrophotography-processing/references/ - every file under
claude/skills/astrophotography-processing/scripts/ claude/skills/astrophotography-processing/README.mdclaude/skills/astrophotography-processing/templates/processing-log.mdclaude/scripts/README.mdclaude/scripts/Validate-SkillFolders.ps1claude/scripts/Validate-SkillQuality.ps1
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 · 586 lines · 29 tokens per session scan A e2b8fc4d3381
upgrade-astrophotography-processing is a command published in the GitHub repository mickpletcher/AI-Skills (19 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 4,859 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-14.
Other commands, from other repositories
literature-review
Review a body of sources by synthesising across them rather than summarising each in turn.
ship-an-mcp-server
Workflow recipe — make your product agent-usable by chaining 4 skills, spec to pricing.
promote
The promote loop — scan your transcripts for what you keep asking, pick a pattern, draft the skill, test its triggers, publish the release package.
rescue-an-account
Workflow recipe — diagnose an at-risk customer and build the full save play through to renewal by chaining 4 skills.
devils-advocate
Stress-test an idea, plan, or decision by arguing against it honestly, to find the flaws before reality does.
linkedin-post
Write a LinkedIn post that reads as a real professional story or insight, with a strong first line and a genuine takeaway.