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/ozmasterai/torus-framework/introspectnpx skills add OZmasterAI/Torus-Framework --skill introspectgit clone --depth 1 https://github.com/OZmasterAI/Torus-FrameworkWhat 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 | $0.00049 | $0.04822 |
| Opus 5 | $0.00024 | $0.02411 |
| Sonnet 5 | $0.00010 | $0.00964 |
| Haiku 4.5 | $0.00005 | $0.00482 |
Grade C, and why
introspect scanned grade C with 2 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 3d 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.
cat ~/.claude/stats-cache.json 2>/dev/null || echo '{}' Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skill-library/*/SKILL.md 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/introspect — Framework Deep Self-Analysis
When to use
When the user says "introspect", "self-analysis", "framework health check", "what needs improvement", "audit the framework", "what's missing", "framework inventory", or wants a structured assessment of the Torus framework's current state.
Hard Limits (read before executing anything)
- Read-only — never modify any files during introspection
- Always search memory for previous introspect results before starting
- Always save results to memory after completing the report
- Show raw numbers in all tables (no rounding percentages to hide detail)
- If any scan step fails, record the failure and continue — partial data is better than none
Phase 1: SCAN — Enumerate All Framework Components
Collect a complete inventory. Run ALL of the following:
Gates:
ls ~/.claude/hooks/gates/gate_*.py 2>/dev/null | sort
ls ~/.claude/hooks/gates/gate_*.py 2>/dev/null | wc -l
For each gate file, extract its gate number and name:
python3 -c "
import os, re
gate_dir = os.path.expanduser('~/.claude/hooks/gates')
gates = sorted(f for f in os.listdir(gate_dir) if f.startswith('gate_') and f.endswith('.py'))
for g in gates:
path = os.path.join(gate_dir, g)
with open(path) as f:
content = f.read()
# Extract gate name from GATE_NAME constant or first docstring
name_match = re.search(r'GATE_NAME\s*=\s*[\"\'](.*?)[\"\']', content)
num_match = re.search(r'gate_(\d+)', g)
lines = content.count('\n')
name = name_match.group(1) if name_match else '(unnamed)'
num = num_match.group(1) if num_match else '?'
print(f' Gate {num:>2}: {g:<30} {lines:>4} lines name={name}')
"
Skills:
ls ~/.claude/skill-library/*/SKILL.md 2>/dev/null
ls ~/.claude/skill-library/*/SKILL.md 2>/dev/null | wc -l
For each skill, extract name and description:
python3 -c "
import os, re
skills_dir = os.path.expanduser('~/.claude/skill-library')
for skill in sorted(os.listdir(skills_dir)):
skill_path = os.path.join(skills_dir, skill, 'SKILL.md')
if os.path.exists(skill_path):
with open(skill_path) as f:
content = f.read()
desc_match = re.search(r'^description:\s*>?\s*\n\s+(.*)', content, re.MULTILINE)
inline_match = re.search(r'^description:\s+(.+)$', content, re.MULTILINE)
desc = (desc_match or inline_match)
desc_text = desc.group(1)[:60] if desc else '(no description)'
lines = content.count('\n')
print(f' {skill:<20} {lines:>4} lines {desc_text}')
"
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.
- 3d ago First seen · 522 lines · 49 tokens per session scan C d213c5424d83
introspect is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 4,822 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…