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/egorfedorov/claude-context-optimizer/smart-loadernpx skills add egorfedorov/claude-context-optimizer --skill smart-loadergit clone --depth 1 https://github.com/egorfedorov/claude-context-optimizerWrote 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/egorfedorov/claude-context-optimizer/smart-loader)<a href="https://agentmods.dev/skills/egorfedorov/claude-context-optimizer/smart-loader"><img src="https://agentmods.dev/badge/skills/egorfedorov/claude-context-optimizer/smart-loader.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 | $0.00043 | $0.00479 |
| Opus 5 | $0.00022 | $0.00239 |
| Sonnet 5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
smart-loader 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.
What it actually says
Smart Context Loader
When a user starts a new task or asks to work on something, check if there are historical patterns that suggest which files they'll need.
When to Activate
- User describes a new task (bug fix, feature, refactor, review)
- User says "let's work on..." or "I need to fix..."
- Session just started and user is describing what they want to do
- User asks "what files do I need for this?"
How to Use
- Check for existing templates matching the task type:
ls ~/.claude-context-optimizer/templates/ 2>/dev/null
- Check historical patterns for the current directory:
node ${CLAUDE_PLUGIN_ROOT}/src/tracker.js suggest "$(pwd)"
- Based on the task description and historical data:
- If a matching template exists, mention it: "I see you have a '{name}' template. Want me to load that context?"
- If historical patterns suggest files, mention: "Based on previous sessions, you usually need these files for this type of task: ..."
- If patterns show files to avoid, mention: "Tip: [file] has been consistently unused in past sessions — I'll skip it."
- If nothing matches, proceed normally
Auto-Optimization Tips
When you detect patterns that waste tokens, proactively suggest improvements:
- If a large file (300+ lines) is being read fully: "I'll use offset/limit to read only the relevant section"
- If a file was wasted in 2+ past sessions: skip it silently or mention why
- If the user's task matches a known template: offer to apply it
Important
- Do NOT automatically read files without user confirmation
- Only SUGGEST, don't force context loading
- Keep suggestions brief (top 3-5 files max)
- If no tracking data exists yet, skip silently — don't mention the optimizer
- Be helpful, not annoying — max 1 suggestion per task start
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 · 43 tokens per session scan A 2864024380e6
smart-loader is a skill published in the GitHub repository egorfedorov/claude-context-optimizer (104 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 479 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 2026-08-30.
Other skills, from other repositories
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive:settings
The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…
alive-cleanup
System maintenance -- stale tasks, orphan folders, unsaved sessions, world health check.
alive-daily
Morning operating system -- sync inputs, read everything, surface priorities, show the day.