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 rajitsaha/100xprism --skill packgit clone --depth 1 https://github.com/rajitsaha/100xprismWrote 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/rajitsaha/100xprism/pack)<a href="https://agentmods.dev/skills/rajitsaha/100xprism/pack"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/pack/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/rajitsaha/100xprism/pack"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/pack.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 | $0.00048 | $0.00738 |
| Opus 5 | $0.00024 | $0.00369 |
| Sonnet 5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade B, and why
pack scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
python3 "$PACKS" "$SUB" "$SLUG" --settings "$HOME/.claude/settings.json" How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pack — Optional Third-Party Skill Packs
Packs are skill collections 100xprism does not ship by default because they only matter to some projects. They are opt-in: nothing installs until you ask.
Scope:
/packinstalls skills you don't have. To authenticate a CLI you already have, use/connect.
Usage
/pack— list every pack, its install state, and anything detected here/pack detect— only what matches the current project/pack add databricks— install a pack/pack remove databricks— reverse what 100xprism installed
Step 1 — Locate the helper
All decisions live in the helper script. Do not reimplement them here.
PACKS=""
for candidate in \
"$HOME/100xprism/adapters/lib/packs.py" \
"$(npm root -g 2>/dev/null)/100xprism/adapters/lib/packs.py"; do
if [ -f "$candidate" ]; then PACKS="$candidate"; break; fi
done
if [ -z "$PACKS" ]; then
echo "100xprism installation not found — reinstall with: npm i -g 100xprism"
exit 1
fi
Step 2 — Route the argument
Pass the user's words through this case statement verbatim. Do not invent a subcommand: anything unrecognised is a usage error, not a guess.
ARG1="${1:-}"
SLUG="${2:-}"
case "$ARG1" in
"") SUB="status" ;;
detect) SUB="detect" ;;
add) SUB="add" ;;
remove) SUB="remove" ;;
*) echo "Usage: /pack [detect | add <slug> | remove <slug>]"; exit 1 ;;
esac
if [ "$SUB" = "add" ] || [ "$SUB" = "remove" ]; then
if [ -z "$SLUG" ]; then
echo "Usage: /pack $SUB <slug> (run /pack to list available slugs)"
exit 1
fi
fi
Step 3 — Run it
"$SLUG" stays quoted so a slug can never split into extra arguments or inject a
flag into the helper.
python3 "$PACKS" "$SUB" "$SLUG" --settings "$HOME/.claude/settings.json"
Step 4 — Report
Print the helper's output verbatim. It already says which platforms were handled and which need a manual step.
If any pack was added or removed, finish with: restart your agent to pick up the change.
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.
- 8d ago First seen · 90 lines · 48 tokens per session scan B 629c3361f11d
pack is a skill published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 11d ago), licensed MIT. It adds 48 tokens to every session and 738 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
engineering-advanced-skills
Index of 37 advanced engineering agent skills for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Use when browsing or choosing among the POWERFUL-tier engineering skills: agent design, RAG, MCP servers, CI/CD, database design, observability, security auditing, changelog/release automation, reliability…
analyzing-windows-lnk-files-for-artifacts
Parse Windows LNK shortcut files to extract target paths, timestamps, volume information, and machine identifiers for forensic timeline reconstruction.
analyzing-memory-forensics-with-lime-and-volatility
Performs Linux memory acquisition using LiME (Linux Memory Extractor) kernel module and analysis with Volatility 3 framework. Extracts process lists, network connections, bash history, loaded kernel modules, and injected code from Linux memory images. Use when performing incident response on compromised Linux systems.
analyzing-active-directory-acl-abuse
Detect dangerous ACL misconfigurations in Active Directory using ldap3 to identify GenericAll, WriteDACL, and WriteOwner abuse paths.
analyzing-windows-amcache-artifacts
Parses and analyzes the Windows Amcache.hve registry hive to extract evidence of program execution, application installation, and driver loading for digital forensics investigations. Uses Eric Zimmerman's AmcacheParser and Timeline Explorer for artifact extraction, SHA-1 hash correlation with threat intel, and…
angular-best-practices
Angular performance optimization and best practices guide. Use when writing, reviewing, or refactoring Angular code for optimal performance, bundle size, and rendering efficiency.