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 agentmods add skills/tlangridge/agent-swarm/context-conservationnpx skills add tlangridge/agent-swarm --skill context-conservationgit clone --depth 1 https://github.com/tlangridge/agent-swarmWrote 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/tlangridge/agent-swarm/context-conservation)<a href="https://agentmods.dev/skills/tlangridge/agent-swarm/context-conservation"><img src="https://agentmods.dev/badge/skills/tlangridge/agent-swarm/context-conservation.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00476 |
| Opus 5 | $0.00011 | $0.00238 |
| Sonnet 5 | $0.00004 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
context-conservation 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 5d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Window Management (CRITICAL)
Your context window is a finite, non-renewable resource within a single session. Once exhausted, you lose the ability to reason about the full picture. Manage it aggressively.
The 6-Step Delegation Cycle
When you have a task that requires substantial code exploration, file reading, or implementation:
- Assess -- Before diving into a large task, estimate if it will consume significant context (many files to read, large codebase exploration, multi-file changes)
- Delegate -- Use a subagent (via the Task tool or by spawning a Claude subagent) for implementation-heavy work
- Scope the delegation -- Give the subagent a precise, self-contained brief: which files, what to change, acceptance criteria
- Preserve your context -- While the subagent works, you retain your high-level understanding without burning context on implementation details
- Review the result -- When the subagent completes, review the output summary rather than re-reading all changed files
- Iterate -- If more work is needed, delegate again with refined instructions
What to Keep in Main Context
- Mission and goals
- Team structure and who is working on what
- Architecture decisions and key interfaces
- Task dependency graph
- Blockers and escalations
What to Delegate to Subagents
- Reading large files or many files
- Writing implementation code
- Running tests and interpreting results
- Codebase exploration and grep searches
- Generating boilerplate or repetitive changes
Warning Signs of Context Exhaustion
- You start forgetting earlier parts of the conversation
- You re-read files you already read
- Your responses become less coherent or miss previously established context
- You lose track of the overall plan
Recovery Strategies
If you notice context pressure:
- Write your current understanding to shared context:
swarm write context.md - Summarize your progress in the task:
swarm task update <id> --desc "Progress: ..." - Complete or hand off your current task
- Focus on coordination rather than implementation
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.
- 5d ago First seen · 52 lines · 22 tokens per session scan A 29018e4405b6
context-conservation is a skill published in the GitHub repository tlangridge/agent-swarm (5 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 476 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…