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 navendubrajesh/context-management-for-agents --skill amazonq-session-managementgit clone --depth 1 https://github.com/navendubrajesh/context-management-for-agentsWrote 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/navendubrajesh/context-management-for-agents/amazonq-session-management)<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/amazonq-session-management"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/amazonq-session-management/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/navendubrajesh/context-management-for-agents/amazonq-session-management"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/amazonq-session-management.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 | $0.00087 | $0.01023 |
| Opus 5 | $0.00044 | $0.00511 |
| Sonnet 5 | $0.00017 | $0.00205 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
amazonq-session-management 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 12d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon Q Session Management
Amazon Q Developer sessions accumulate chat history, tool outputs, and loaded rules in a bounded context window. Compaction (/compact) replaces detailed history with a summary; clear (/clear) wipes it entirely. The CLI adds auto-compaction when validation errors occur. This skill covers monitoring and hygiene for long Q sessions.
When to Activate
Activate this skill when:
- Q suggests compaction or context approaches ~80% capacity (IDE nudge)
- A Q CLI session fails with context window validation errors
- Planning multi-phase work in one
q chatsession - Deciding between
/compact,/clear, or starting a new tab/session - Auditing what Q preserved after compaction
Do not activate this skill for adjacent work owned by other skills:
- Do not activate for
.amazonq/rules/authoring:amazonq-customization. - Do not activate for rule glob loading and token limits:
amazonq-context-architecture. - Do not activate for Copilot CLI checkpoints:
copilot-session-management. - Do not activate for platform-agnostic compression algorithms:
context-compression.
Core Concepts
What fills the window
- System instructions and tool definitions (fixed overhead)
- Loaded project rules from
.amazonq/rules/ - User messages and Q responses
- Tool call inputs and outputs (often largest contributor)
- Explicitly added files via IDE context picker or CLI
/context add
Manual compaction: /compact
Enter /compact in chat. Q generates a concise summary preserving goals, work done, key technical details, important files, and next steps. The summary replaces detailed history for model reasoning while the full transcript may remain visible until session end (IDE).
Use proactively at phase boundaries — before starting test/refactor/PR phases.
Automatic compaction nudge (IDE)
At approximately 80% of context capacity, Q displays a notification suggesting compaction. Accept when transitioning phases; defer only if mid-critical-step and few turns remain.
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.
- 12d ago First seen · 87 lines · 87 tokens per session scan A 76984318b56e
amazonq-session-management is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,023 once invoked, about $0.0004 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.