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.
git 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/commands/egorfedorov/claude-context-optimizer/orchestrate)<a href="https://agentmods.dev/commands/egorfedorov/claude-context-optimizer/orchestrate"><img src="https://agentmods.dev/badge/commands/egorfedorov/claude-context-optimizer/orchestrate/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/commands/egorfedorov/claude-context-optimizer/orchestrate"><img src="https://agentmods.dev/badge/commands/egorfedorov/claude-context-optimizer/orchestrate.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 | $0.00000 | $0.00451 |
| Opus 5.5 | $0.00000 | $0.00180 |
| Sonnet 5.5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
orchestrate 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 today.
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
Orchestrate:
Needs Claude Code or Cowork: the
scoutandrunnersubagents don't load in claude.ai chat. There, do the task directly and suggestfresh-startwhen the conversation gets long.
Do this task as an orchestrator. The aim is the same result at a fraction of the cost: in a long session, every token in this conversation is re-read on each later request, while a subagent's reading is discarded when it returns. The plugin's subagents run on Haiku 5.5, about 40× cheaper per token than Opus 5.5.
How to split the work
- Understand (delegate). List the questions you need answered before you
can change anything: where is X defined, how does Y flow, what calls Z,
what do the docs say about W. Send each independent question to a
context-optimizer:scoutsubagent, several in parallel when they don't depend on each other. Write each prompt as a precise question with the names, paths or URLs you already know, and ask forpath:lineevidence. - Decide (yourself). Plan from the scouts' answers. Read yourself only the exact line ranges you are about to edit.
- Change (yourself). Make the edits here. Don't hand edits or design decisions to a subagent.
- Verify (delegate). Send the exact test, build or lint commands to a
context-optimizer:runnersubagent and act on its failure report. Fix, then send the runner again until it passes. - Report. What changed, why, and what was verified.
When not to delegate
- One known file or one grep: do it yourself; a subagent's startup costs more.
- Work that needs many back-and-forth steps on shared context.
- Anything that changes files, or needs judgment about the design.
If this conversation is already past ~150K tokens, suggest /compact before
starting a large task.
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.
- today First seen · 36 lines · 0 tokens per session scan A d868c8529590
orchestrate is a command published in the GitHub repository egorfedorov/claude-context-optimizer (116 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 451 tokens. 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 2026-10-18.
Other commands, from other repositories
dock-chat
Dock the full conversation to Telegram — drive Claude from your phone.
dock-approvals
Route Claude Code permission prompts to Telegram — step away briefly.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
help
Explain Ralph Wiggum technique and available commands.
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
ashlr-eco-mode
Toggle eco mode — aggressive token-saving behaviors that trade some response richness for lower session cost.