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 DDS-Solutions/AI-TadPole-OS --skill context-compressiongit clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OSWrote 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/dds-solutions/ai-tadpole-os/context-compression)<a href="https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/context-compression"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/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/dds-solutions/ai-tadpole-os/context-compression"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/context-compression.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 | $0.00038 | $0.01068 |
| Opus 5.5 | $0.00015 | $0.00427 |
| Sonnet 5.5 | $0.00008 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[!IMPORTANT] AI Context & Knowledge Heritage
- Subsystem: Agent Skills Registry / context-compression
- Architecture:
@docs ARCHITECTURE:Documentation- Failure Path: Context degradation, attention dilution, or loss of critical architectural decisions.
- Observability: Traceability via
execution/parity_guard.py([SKILL])
Context Compression & Session Management
Purpose: Prevent context degradation, attention dilution, and hallucination drift in long-running multi-turn sessions (20+ turns) by distilling working memory into high-signal checkpoints. Workflow Bindings: Integrated into
/orchestrateand/onboard.
📚 Progressive Disclosure & L3 Reference Index
Consult deep L3 Reference Guides and verification tools on demand:
- Checkpoint & Handoff Templates: checkpoint_and_handoff_templates.md
- Deterministic Context Compactor: context_compactor.py
🚦 1. Compression Triggers & The 3-Tier Model
| Level | Scope | Trigger Condition | Execution Action & Output Target |
|---|---|---|---|
| Level 1: Micro-Compact | Large Tool Dumps | Grep, search, or file reads $> 100$ lines | Summarize key files, matched line numbers, and counts. Discard raw dump. |
| Level 2: Phase Transition | Lifecycle State Shift | Moving from Brainstorming $\rightarrow$ Coding | Record confirmed architectural choices; purge transient read logs. |
| Level 3: Session Checkpoint | Full Working Memory | 20+ turns or user requests summary | Emit full 5-section Session Checkpoint to .tmp/handoffs/session_checkpoint.md. |
🧭 2. Preservation vs Discard Directives
Preserve at All Costs:
├── Core Architectural Decisions & Rationale (the "Why")
├── Exact File Paths & Symbols Touched
├── Executable Verification Commands & Test Results
└── Active Blockers and Next Milestones
Discard Aggressively:
├── Full file contents already committed to disk
├── Repetitive tool invocation syntax and error retries
├── Raw directory trees and verbose package manifests
└── Ephemeral conversational filler and intermediate banter
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.
- 9d ago Changed · +46 lines 924816fd2562
- 1mo ago First seen · 46 lines · 38 tokens per session scan A 9fc9d71895bd
context-compression is a skill published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 1,068 once invoked, about $0.0002 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
build-with-tinybase
Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, resolving TinyBase import paths, configuring browser or database…
optimizing-clickhouse-and-hogql-queries
Workflow for optimizing ClickHouse and HogQL queries. Use when a HogQL query, query runner, insight, or report is too slow; when a hand-written ClickHouse query (via syncexecute or in a migration) is too slow; when ClickHouse times out or hits memory limits; when investigating a slow system.querylog row; or when…
generating-clickhouse-query-performance-reports
Produce and structure slow-query performance reports for PostHog's production ClickHouse (US and EU). Use when asked for a slow query report, query performance analysis over the last N days, per-team query cost, OOM or timeout investigation, cluster cost/memory regressions, or materialization candidates. Covers the…
query-clickhouse-via-metabase
Run ClickHouse system.querylog analysis via the internal Metabase API. Use when investigating slow queries, materialization candidates, per-team query performance, ClickHouse cost or memory issues, or any system.querylog question. Covers prod-us and prod-eu, SSO-gated cookie auth via hogli, and ready-to-run query…
context-layer-dreaming
Synthesizes recent organizational activity into a durable context wiki. Use when running a nightly or incremental context-layer dream, or when updating sourced organizational context from completed work.
context-layer-consolidation
Keep the context wiki coherent using the deterministic lint report queue.