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 area-lessonsgit 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/area-lessons)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/area-lessons"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/area-lessons/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/area-lessons"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/area-lessons.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 | $0.00071 | $0.00842 |
| Opus 5.5 | $0.00028 | $0.00337 |
| Sonnet 5.5 | $0.00014 | $0.00168 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
area-lessons scanned grade A with 1 finding 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 25d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Read-only: one `curl` GET against the daemon on `localhost:7777`, nothing else How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
List the ACTIVE lessons whose area globs overlap the current directory, read
from the local swarmery daemon (GET /api/lessons?status=active&area=<dir>).
Headless phase and plan runs already receive these lessons in their prompt;
interactive sessions get them only when the operator asks, through this skill.
Nothing here writes a file, a memory entry, or a hook.
Rules (never violate)
- Read-only: one
curlGET against the daemon onlocalhost:7777, nothing else that changes state. - Never copy lessons into
MEMORY.md,CLAUDE.md, settings, or any hook. A lesson that belongs inCLAUDE.mdis promoted from the daemon's Lessons page, which commits it on a new branch for review. - Quote each lesson with its id (
[L-12]), so a later reply can cite the one it relied on. - When the daemon is not reachable, say so in one line and stop. Never guess lessons.
Procedure
- Resolve the directory relative to the repository root:
git rev-parse --show-prefix(empty at the root; then use.). - Query the daemon, URL-encoding the directory:
curl -s --globoff "http://localhost:7777/api/lessons?status=active&area=<dir>" - Render
lessons[]as one line each,- [L-<id>] <guidance> (areas: <areaGlobs>), newest first as returned. An empty list is a valid answer: "No active lessons for<dir>."
How to use
What it does
Shows the lessons that earlier headless runs in this project learned about the directory you are in: one line per lesson with its citable id, its guidance and the areas it applies to. It reads them from the local daemon and changes nothing. The same matcher decides which lessons a headless run receives.
When to use it
- You are about to work by hand in a directory that headless runs touched before, and want what they learned.
- You want to check which lessons a phase in this area would be handed.
Not for reviewing, accepting, retiring or promoting lessons: that is the daemon's
Lessons page. Not for code search either (code-search).
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.
- 25d ago First seen · 89 lines · 71 tokens per session scan A fc6d2c74135f
area-lessons is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 842 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.
Other skills, from other repositories
agentmemory-agents
How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.
memory-retain
Save what was learned to Hindsight long-term memory. Use when a task finishes, when the user states a fact, decision or preference, and when you discover something a later run or another Bot would need.
md-fetch-summarize
Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…
sl_capture
How to capture new reusable patterns into ktx's semantic layer - when a measure, segment, or join belongs in the catalog and how to write it generically so it stays small and useful over time. Loaded by the post-turn memory-agent only. The research agent does not write to the SL.
ctx-purge
Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge.
handoff
Save state at the end of a session, or resume from the last one. Triggers "wrapping up", "running out of context", "done for today", "continue where we left off", "resume".