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 skills add IchenDEV/prompt-optimizer-plugins --skill audit-gpt-6-astra-skillsgit clone --depth 1 https://github.com/IchenDEV/prompt-optimizer-pluginsWrote 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/skills/ichendev/prompt-optimizer-plugins/audit-gpt-6-astra-skills)<a href="https://agentmods.dev/skills/ichendev/prompt-optimizer-plugins/audit-gpt-6-astra-skills"><img src="https://agentmods.dev/badge/skills/ichendev/prompt-optimizer-plugins/audit-gpt-6-astra-skills/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/skills/ichendev/prompt-optimizer-plugins/audit-gpt-6-astra-skills"><img src="https://agentmods.dev/badge/skills/ichendev/prompt-optimizer-plugins/audit-gpt-6-astra-skills.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 | $0.00078 | $0.01056 |
| Opus 5.5 | $0.00031 | $0.00422 |
| Sonnet 5.5 | $0.00016 | $0.00211 |
| Haiku 4.5 | $0.00008 | $0.00106 |
Grade A, and why
audit-gpt-6-astra-skills 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit GPT-6 Astra Skills and Agent Scaffold
Audit repository Skills, AGENTS.md, and task prompts for GPT-6 Astra. Prefer subtractive cleanup over adding rules. Preserve intentional safety boundaries; remove obsolete handholding that now causes pauses, wrong skill loads, over-testing, or context burn.
Sources
Read references/practitioner-guidance.md for the checklist and bad/good examples. Canonical source: Eric Provencher, Rethinking skills and prompts for GPT-6 Astra. For copy-ready product prompts and API migration, use $optimize-gpt-6-astra-prompts / Using GPT-6 Astra.
Workflow
1. Scope the audit
Identify what exists in the working tree or paths the user named:
- skill directories (
SKILL.mdfrontmatter descriptions, bodies, bundled scripts/references); AGENTS.md/ equivalent always-on instruction files;- recurring task prompts, system prompts, or harness defaults that force read-all / ask-first / always-test behavior.
Ask only if the audit target is unclear. Otherwise proceed.
2. Diagnose against Astra failure modes
Flag only issues that match observed or likely Astra behavior:
| Symptom | Likely cause |
|---|---|
| Wrong or extra skills load | Long, overlapping, contradictory, or "pick me" descriptions; description truncation under many skills |
| Early pause or redundant approval | Strong ask-first language; unclear completion; skill vs user conflicts |
| Slow typo-sized edits | Always-read-full-repo or always-read-docs-first rules |
| Excessive tests on small changes | Sol-era "always run the full suite" encouragement |
| Stops after a first draft | Missing completion criteria or exploration bounds |
| Overconstrained on Astra but fine on Sol/Luna | Recipe-style skills written for weaker models |
3. Propose surgical edits
For each finding, return:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +1 lines · -5 tokens per session 3c74db9b2660
- 1mo ago First seen · 86 lines · 83 tokens per session scan A 5525200bf10d
audit-gpt-6-astra-skills is a skill published in the GitHub repository IchenDEV/prompt-optimizer-plugins (6 stars, last pushed 20d ago), licensed MIT. It adds 78 tokens to every session and 1,056 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
sol-terra-luna-auto-router
Optimize quality per token across GPT Codex, GPT Work, and Codex CLI by automatically selecting the best-fit GPT-5.6 Luna, Terra, or Sol profile and reasoning effort for the main task and every delegated subtask. Prioritize direct visible Codex execution and importance-aware subagent routing. Use automatically for…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.