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 atretyak1985/swarmery --skill context-optimizationgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/context-optimization)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/context-optimization"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/context-optimization/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/atretyak1985/swarmery/context-optimization"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/context-optimization.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 | $0.00038 | $0.00841 |
| Opus 5.5 | $0.00015 | $0.00336 |
| Sonnet 5.5 | $0.00008 | $0.00168 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
context-optimization 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Plan what to read before reading it. On a task spanning several files or repos,
turn "open everything and hope" into a short ordered context plan: which files,
which line ranges, in which phase, and where to /clear between them. It changes
no code — it governs loading so the skills that do the work keep room to think.
Rules (never violate)
- Run
codebase-retrievalbefore any full-file read; discovery precedes loading. - Read with offset/limit — never whole files when one function is the target.
- Keep files loaded ≤ 3× files actually edited; record the ratio in the plan.
- Suggest
/clearat every repo switch and at every phase boundary that frees files. - At ≥40% window usage, delegate any isolatable read (one whose product is a digest) to a leaf subagent at depth-1 — never leaf → leaf.
- Confidence LOW after discovery means stop and ask, not a plan you half-trust.
Resources
- Read
resources/planning-procedure.mdbefore planning: the 7-step procedure, the repo/glob map, the step-7 delegation decision table (40% / 60% thresholds), the plan template, self-check, escalation triggers, failure modes, and a worked two-phase example.
How to use
What it does
Produces a context plan: targeted reads in phases, /clear decisions with
reasons, and a loaded-versus-edited budget with a confidence rating. It runs
discovery first, so the plan names real files rather than guesses.
When to use it
- The task touches 3 or more files, in one repo or across several.
- The task crosses a repo boundary —
apps/<mainApp>plus<device>, say. - Your window is already past 40% and more reads are coming.
- You are about to load a large module tree just to extract a verdict or a list.
Not for: single-file edits (just make them); a read-only question about one
function (code-search); or work already running inside a scoped subagent — that
isolation is what this skill would have bought you.
How to invoke
Skill(skill: "core:context-optimization")
Task: fix telemetry latency between the device/edge repo and the main app
Repos: apps/<mainApp>, <device>
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 84 lines · 38 tokens per session scan A f76dee09cae2
context-optimization is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 841 once invoked, about $0.0002 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
dependency-versions
MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, planning or writing CI/CD workflows (GitHub Actions, CircleCI…
finish
Ship phase — merge, PR, keep, or discard with pre-merge verification.
gws-quick-ref
Quick reference for gws CLI syntax — core patterns, key flags, pagination, field masks, and output formats.
excalidraw
Create or extend editable Excalidraw diagrams from descriptions or repository evidence using a local skeleton-to-scene converter.
style-ops
Maintain, validate or report on the Fakoli principles ledger, checking evidence pointers and keeping its Markdown projection synchronized.
gws-events-subscribe
Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.