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 ils15/pantheon-legacy --skill token-auditgit clone --depth 1 https://github.com/ils15/pantheon-legacyWrote 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/ils15/pantheon-legacy/token-audit)<a href="https://agentmods.dev/skills/ils15/pantheon-legacy/token-audit"><img src="https://agentmods.dev/badge/skills/ils15/pantheon-legacy/token-audit/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/ils15/pantheon-legacy/token-audit"><img src="https://agentmods.dev/badge/skills/ils15/pantheon-legacy/token-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 63 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Agent Snooping · line 63 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00022 | $0.01278 |
| Opus 5.5 | $0.00009 | $0.00511 |
| Sonnet 5.5 | $0.00004 | $0.00256 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
token-audit scanned grade A 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 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.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
find .github/skills .claude/skills .opencode/skills -name "SKILL.md" 2>/dev/null | xargs wc -l 2>/dev/null Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token Audit — Repository Context Optimization
Purpose
When Pantheon is installed in a new repository, run this skill to audit and optimize all AI context files for token efficiency.
Step 1: Discover Context Files
Scan the repository for ALL files that contribute to AI context:
# Auto-loaded files (every invocation)
AGENTS.md
CLAUDE.md
.gemini/AGENTS.md
.github/copilot-instructions.md
.github/instructions/*.md
.claude/CLAUDE.md
.cursor/rules/*.mdc
.windsurfrules
.kilocode/rules/*.md
.clinerules
.opencode/agents/*.agent.md
# Memory bank
docs/memory-bank/*.md
docs/adr/*.md
# Skills (lazy-load)
.github/skills/*/SKILL.md
.claude/skills/*/SKILL.md
.opencode/skills/*/SKILL.md
Step 2: Build Redundancy Map
Read all discovered files and map what information appears where:
| Information | Found in files | Lines duplicated |
|---|---|---|
| Tech stack | AGENTS.md, 00-overview.md, copilot-instructions.md | ~15 |
| Run commands | AGENTS.md, 03-tech-context.md, commands.md | ~10 |
| Agent roles | AGENTS.md, copilot-instructions.md, zeus.agent.md | ~20 |
| CI/CD rules | AGENTS.md, copilot-instructions.md, .github/workflows | ~12 |
| Coding standards | copilot-instructions.md, instructions/*.md | ~25 |
Step 3: Measure Baseline
Count lines and estimate tokens:
# Auto-loaded context (every invocation)
wc -l AGENTS.md .github/copilot-instructions.md /memories/repo/*.md 2>/dev/null
# On-demand context (read by agents)
wc -l docs/memory-bank/*.md 2>/dev/null
# Skills (lazy-load)
find .github/skills .claude/skills .opencode/skills -name "SKILL.md" 2>/dev/null | xargs wc -l 2>/dev/null
# Agent definitions
wc -l .github/agents/*.agent.md .opencode/agents/*.agent.md .claude/agents/*.agent.md 2>/dev/null
Estimate: 1 line ≈ 4 tokens (markdown average)
Step 4: Identify Red Flags
Check for content that should NOT be auto-loaded. Use specific patterns, not generic keywords:
- Wave delivery tables:
Wave 1:,Wave 2:,## Wave,wave-by-wave(NOT "DAG Waves" pattern) - Delivery history:
delivered:,what was delivered,delivery history,delivery log - Progress metrics:
[0-9]+% complete,commit count,commits: [0-9](NOT in progress-log.md) - Last-updated dates:
**Last Updated**:,<!-- last.updated:(git has this) - Cleanup logs:
deleted X lines of dead code,legacy cleanup,cleaned up X - Duplicated tech stack: same phrase in >3 files (use long phrases, not single words)
- Files exceeding line limits: AGENTS.md >80, memory-bank >100
- Empty or near-empty files that waste discovery overhead
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 First seen · 148 lines · 22 tokens per session scan A 1d36efffd3af
token-audit is a skill published in the GitHub repository ils15/pantheon-legacy (12 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,278 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…