context-conservation

context-conservation is a skill for Claude Code from tlangridge/agent-swarm. It costs 22 tokens per session (476 once invoked), scanned A, original, MIT.

A set of practices for managing an AI coding agent’s limited working context and assigning large tasks to helper agents.

In plain words
What is it for?
It is for splitting substantial development tasks into focused assignments, preserving key context, reviewing results, and continuing with follow-up work.
Why use it?
It helps prevent important goals and decisions from being lost during long code exploration or implementation work.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Good fit It is for splitting substantial development tasks into focused assignments, preserving key context, reviewing results, and continuing with follow-up work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tlangridge/agent-swarm/context-conservation
Install

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.

Any agent
npx skills add tlangridge/agent-swarm --skill context-conservation
Clone the repo
git clone --depth 1 https://github.com/tlangridge/agent-swarm

Made for: Claude Code.

Wrote 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.

agentmods badge for context-conservation

README.md
[![agentmods](https://agentmods.dev/badge/skills/tlangridge/agent-swarm/context-conservation/github.svg)](https://agentmods.dev/skills/tlangridge/agent-swarm/context-conservation)
Your own site
<a href="https://agentmods.dev/skills/tlangridge/agent-swarm/context-conservation"><img src="https://agentmods.dev/badge/skills/tlangridge/agent-swarm/context-conservation/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.

agentmods 80×15 button for context-conservation

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 476 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00476
Opus 5.5 $0.00009 $0.00190
Sonnet 5.5 $0.00004 $0.00095
Haiku 4.5 $0.00002 $0.00048

Measured 2mo ago against content hash 29018e4405b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

skills/context-conservation/SKILL.md · 52 lines

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:

  1. Assess -- Before diving into a large task, estimate if it will consume significant context (many files to read, large codebase exploration, multi-file changes)
  2. Delegate -- Use a subagent (via the Task tool or by spawning a Claude subagent) for implementation-heavy work
  3. Scope the delegation -- Give the subagent a precise, self-contained brief: which files, what to change, acceptance criteria
  4. Preserve your context -- While the subagent works, you retain your high-level understanding without burning context on implementation details
  5. Review the result -- When the subagent completes, review the output summary rather than re-reading all changed files
  6. 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:

  1. Write your current understanding to shared context: swarm write context.md
  2. Summarize your progress in the task: swarm task update <id> --desc "Progress: ..."
  3. Complete or hand off your current task
  4. Focus on coordination rather than implementation

Read the full file on GitHub · 52 lines

Changes

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.

  1. 2mo ago First seen · 52 lines · 22 tokens per session scan A 29018e4405b6

Subscribe to this mod's changes

context-conservation is a skill published in the GitHub repository tlangridge/agent-swarm (5 stars, last pushed 8mo ago), licensed MIT. It adds 22 tokens to every session and 476 once invoked, about $0.0001 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.

Related

context-conservation compared with skills from other repositories

context-conservation next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
context-conservationtlangridge/agent-swarmSkill58mo agoMITA22Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code