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 eddiebelaval/squire --skill context-managergit clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/eddiebelaval/squire/context-manager)<a href="https://agentmods.dev/skills/eddiebelaval/squire/context-manager"><img src="https://agentmods.dev/badge/skills/eddiebelaval/squire/context-manager/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/eddiebelaval/squire/context-manager"><img src="https://agentmods.dev/badge/skills/eddiebelaval/squire/context-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 11 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00012 | $0.02043 |
| Opus 5.5 | $0.00005 | $0.00817 |
| Sonnet 5.5 | $0.00002 | $0.00409 |
| Haiku 4.5 | $0.00001 | $0.00204 |
Grade A, and why
Context Manager 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 1mo 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Manager
The Context Manager skill helps you optimize conversation context to maintain Claude's effectiveness throughout long sessions. It tracks context window usage, identifies when to summarize or prune context, and helps you structure conversations to keep relevant information accessible while staying within token limits.
This skill is essential for complex, multi-day projects where conversation history grows large. It helps you decide what to preserve, what to summarize, and what to discard, ensuring Claude maintains awareness of important decisions and project state without hitting context limits.
Use this skill proactively during long development sessions, before starting new major features, or when you notice performance degradation due to context bloat.
Core Workflows
Workflow 1: Monitor Context Health
- Check current context usage:
- Token count
- Percentage of limit
- Recent growth rate
- Analyze context composition:
- How much is code?
- How much is conversation?
- How much is documentation?
- Identify problematic areas:
- Redundant information
- Outdated references
- Irrelevant tangents
- Assess risk level:
- Green: <50% usage, healthy
- Yellow: 50-75% usage, monitor
- Red: >75% usage, take action
- Recommend actions if needed
- Report status to user
Workflow 2: Summarize Long Conversation
- Review conversation history
- Extract key information:
- Decisions made
- Problems solved
- Current project state
- Open questions
- Next steps
- Organize by topic/timeline
- Create concise summary
- Validate with user
- Suggest starting new thread with summary
Workflow 3: Prune Irrelevant Context
- Identify candidates for removal:
- Resolved issues
- Abandoned approaches
- Temporary debugging
- Superseded information
- Categorize by importance:
- Safe to remove
- Could summarize
- Must preserve
- Propose pruning plan to user
- Execute approved removals
- Preserve critical context
- Verify coherence after pruning
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.
- 1mo ago First seen · 295 lines · 12 tokens per session scan A 803d31ba8986
Context Manager is a skill published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 2,043 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
Context Manager
Manage conversation context and memory for optimal AI performance.
context-engineering
Use this skill for optimizing AI context windows. Covers context sizing, prioritization, and avoiding context overflow.
remember
Write-side memory: stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Use when something worth persisting across sessions was just learned or decided. To search or read existing memory, invoke memory; to debug retrieval internals…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…
layered-context
L0/L1/L2 three-layer context loading protocol — reduces token consumption during /resume boot.
furl
How the Furl context-compression plugin works in Claude Code and Codex — the furlcompress / furlretrieve / furlstats / furlpurge / furlsearch / furllist MCP tools, the > retrieval flow, and Claude Code's optional automatic hooks. Use when the user asks what Furl is doing, how to compress or retrieve content, why…