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 synthesisengineering/synthesis-skills --skill synthesis-context-lifecyclegit clone --depth 1 https://github.com/synthesisengineering/synthesis-skillsWrote 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/synthesisengineering/synthesis-skills/synthesis-context-lifecycle)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-context-lifecycle"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-context-lifecycle/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/synthesisengineering/synthesis-skills/synthesis-context-lifecycle"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-context-lifecycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.12383 |
| Opus 5 | $0.00028 | $0.06191 |
| Sonnet 5 | $0.00011 | $0.02477 |
| Haiku 4.5 | $0.00006 | $0.01238 |
Grade A, and why
synthesis-context-lifecycle 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 yesterday.
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 — 943 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Lifecycle Management
The Problem
AI collaborators start every session with zero context. Their effectiveness depends entirely on the quality of the context they receive. For short-lived projects (2-3 sessions), a single context file works. For long-running projects spanning weeks or months, that file grows unboundedly — combining four types of information with fundamentally different lifecycles:
| Information type | Access pattern | Growth pattern | Ideal treatment |
|---|---|---|---|
| Working memory (current state, active tasks) | Every session | Constant | Keep lean, refresh often |
| Episodic memory (session logs) | Rarely after 1 week | Unbounded append | Archive monthly |
| Semantic memory (stable facts, reference) | Most sessions | Slow, update-in-place | Separate file |
| Completed work records | Almost never | Unbounded append | Delete after archiving |
Combining all four in one file means the file grows linearly with session count, with no mechanism for information to leave. This is the classic hot/warm/cold data problem from database engineering, manifesting in AI context management.
The Architecture
Three Tiers
project/
├── CONTEXT.md # Working memory (budget: ≤150 lines)
├── REFERENCE.md # Semantic memory (stable facts, update in place)
├── reference/ # Semantic memory, sharded — once one file is not enough
│ └── <topic>.md # One topic per file; REFERENCE.md becomes its index
├── sessions/ # Episodic memory (archived session logs)
│ └── YYYY-MM.md # Monthly files
└── [other files] # Transcripts, artifacts, etc.
This maps to both cognitive science and systems engineering:
| Human memory | CPU cache | Synthesis equivalent | Properties |
|---|---|---|---|
| Working memory | L1 cache | CONTEXT.md | Small capacity, constantly refreshed, always loaded |
| Semantic memory | L2 cache | REFERENCE.md | Facts and relationships, updated in place, loaded on demand |
| Episodic memory | L3 cache | sessions/ | Chronological events, append-only, searched when needed |
| Procedural memory | Firmware | CLAUDE.md / AGENTS.md + lessons/ | How to do things, rules, patterns |
What ships with it
12 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.
- agents/openai.yaml 224 B
- scripts/context_currency.py 24 KB runs code
- scripts/context_doctor.py 75 KB runs code
- scripts/context_edit.py 23 KB runs code
- scripts/review_ledger.py 9.5 KB runs code
- scripts/test_body_currency.py 8.0 KB runs code
- scripts/test_context_currency.py 11 KB runs code
- scripts/test_context_doctor.py 60 KB runs code
- scripts/test_context_edit.py 18 KB runs code
- scripts/test_intake_routing.py 3.4 KB runs code
- scripts/test_item_currency.py 11 KB runs code
- scripts/test_review_ledger.py 8.1 KB runs code
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.
- yesterday Changed · +14 lines d4871060dc00
- 4d ago Changed · +6 lines 3dbded78bf3c
- 5d ago Changed · +12 lines 86a72857a6ae
- 5d ago Changed · +81 lines ff8546a8e705
- 9d ago First seen · 830 lines · 57 tokens per session scan A 1cfa16159a08
synthesis-context-lifecycle is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 12,383 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.