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 abstractonion/cadence --skill manage-context-windowgit clone --depth 1 https://github.com/abstractonion/cadenceWrote 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/abstractonion/cadence/manage-context-window)<a href="https://agentmods.dev/skills/abstractonion/cadence/manage-context-window"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/manage-context-window/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/abstractonion/cadence/manage-context-window"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/manage-context-window.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 | $0.00033 | $0.00418 |
| Opus 5 | $0.00016 | $0.00209 |
| Sonnet 5 | $0.00007 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
manage-context-window 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 8d 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.
What it actually says
Manage your context window
A long session degrades. Vague language, skipped steps, half-finished tasks, and the same bug "fixed" three different ways are all symptoms of context pressure. Notice it early — quality drops gradually, well before any hard limit fires.
What to do, in order of preference
- Read narrowly. Use search to land on the few lines you need; don't paste whole files when a snippet suffices. Skim summaries or frontmatter before bodies.
- Delegate heavy reads. If answering one question would require loading a large file or long trace into main context, hand that question to a subagent and consume only its summary (see
delegate-with-fresh-context). - Checkpoint. When a long session is getting hazy, write the current state — what's done, what's next, what's known, what's unresolved — to a durable artifact (a PR description, a scratch doc, a TODO at the top of the file) so a fresh session can pick up cleanly.
- Hand off. If a phase is finished, end the session and start the next one clean. Don't push one more task through a polluted context just because you're already there.
Warning signs you're already degraded
- You're reaching for "appropriate handling" or "standard pattern" instead of writing the actual code.
- You're skipping steps you'd normally do (tests, runtime checks, scope diff).
- A change you "just made" doesn't show up in the diff.
- You've fixed the same symptom more than once.
When you notice these: stop, summarize what's true, and either delegate the next piece or hand off to a fresh session.
What's worth keeping in main context
The plan, the user's stated intent, the current diff, and the next verification command. Everything else is recoverable on demand.
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.
- 8d ago First seen · 29 lines · 33 tokens per session scan A ced0c2972323
manage-context-window is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 418 once invoked, about $0.0002 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 2026-08-31.
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.