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 context-compressiongit 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/context-compression)<a href="https://agentmods.dev/skills/ils15/pantheon-legacy/context-compression"><img src="https://agentmods.dev/badge/skills/ils15/pantheon-legacy/context-compression/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/context-compression"><img src="https://agentmods.dev/badge/skills/ils15/pantheon-legacy/context-compression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 Privilege Escalation · line 401 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium System Prompt Leakage · line 168 Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
- medium Agent Snooping · line 859 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.
- medium Agent Snooping · line 860 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 | $0.00032 | $0.10159 |
| Opus 5.5 | $0.00013 | $0.04064 |
| Sonnet 5.5 | $0.00006 | $0.02032 |
| Haiku 4.5 | $0.00003 | $0.01016 |
Grade A, and why
context-compression 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 — 862 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Compression — Level 2 (Intelligent Compression)
Level 2 replaces Level 1 with priority-aware compression: scoring, semantic summarization for critical/high entries, downstream-aware field masks, budget allocation, and automatic cross-references. Zeus triggers, Mnemosyne executes.
1. Overview
Level 2 adds four capabilities beyond Level 1:
- Priority Scoring Engine — Deterministic keyword-driven scoring (no LLM) for each subtask_summary across 5 dimensions. Outputs CRITICAL/HIGH/MEDIUM/LOW.
- Semantic Summarization — Template-generated contextual summaries for CRITICAL/HIGH entries, tailored to the downstream agent pair. MEDIUM/LOW get standard mechanical 1-line compression.
- Downstream-Aware Compression — Field masks preserve the most relevant fields per (from_agent, to_agent) pair. Themis gets all fields; Mnemosyne gets minimal.
- Cross-Reference Mechanism — Auto-generated
_xref/index.mdwith entity references for endpoints, tables, migrations, components, and decisions, surviving sprint boundaries.
Budget allocation is priority-greedy. CRITICAL entries are always expanded. Overflow escalates to Zeus.
2. Compression Triggers
Same 7 triggers as Level 1, with Level 2 behavior:
| Trigger | Fires | Level 2 Behavior |
|---|---|---|
| C1 Phase Gate | Themis APPROVED | Priority-score subtask_summary → semantic summary (CRITICAL/HIGH) or 1-line (MEDIUM/LOW) → 01-active-context.md |
| C2 Phase Gate | Themis APPROVED | IMPL artifact → scored, archived to 02-progress-log.md; .tmp/ deleted |
| C3 Phase Gate | Themis APPROVED | REVIEW summary line → 02-progress-log.md; .tmp/ deleted |
| C4 Feature Complete | Last phase APPROVED | PLAN reference → 01-active-context.md; .tmp/ deleted |
| C5 Sprint Close | @mnemosyne Close sprint |
Bulk cleanup + cross-ref archive + flag unresolved |
| C6 Explicit | /compress |
Per-type compression with priority scoring |
| C7 Size-based | 01-active-context.md Completed Phases > 100 lines |
Priority-greedy trim: oldest LOW entries first, preserving CRITICAL and HIGH |
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 · 862 lines · 32 tokens per session scan A 07cfddfedeb8
context-compression is a skill published in the GitHub repository ils15/pantheon-legacy (12 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 10,159 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 2026-08-31.
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…