Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atretyak1985/swarmery/plugin install coreWrote 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/atretyak1985/swarmery/land)<a href="https://agentmods.dev/commands/atretyak1985/swarmery/land"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/land/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/atretyak1985/swarmery/land"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/land.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 | $0.00034 | $0.02901 |
| Opus 5 | $0.00017 | $0.01451 |
| Sonnet 5 | $0.00007 | $0.00580 |
| Haiku 4.5 | $0.00003 | $0.00290 |
Grade A, and why
land 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 6d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/land — land the plane
Run this before you stop working on a session that touched real tasks. It reconciles the agent-workspace task cards with what this session actually did, so the next session (yours or a teammate's) starts from an accurate state instead of re-deriving it. "Land the plane" = leave the runway clear: nothing half-flipped, nothing undocumented, one clear next step.
Work the checklist top to bottom. Each step is a small, verifiable action — do the work, don't narrate it. Finish with the landing report in step 7.
Paths used throughout: the task CLI is the plugin's
${CLAUDE_PLUGIN_ROOT}/bin/agent-work.sh. It resolves the workspace from
AGENT_PROJECT (+ optional AGENT_WORKSPACE_ROOT); without AGENT_PROJECT it falls
back to a legacy project-local .claude-workspace/.
AW="${CLAUDE_PLUGIN_ROOT}/bin/agent-work.sh"
WS="${AGENT_WORKSPACE_ROOT:-$HOME/swarmery-workspace}/${AGENT_PROJECT:-}/workspace"
[ -d "$WS" ] || WS="${CLAUDE_PROJECT_DIR:-.}/.claude-workspace" # legacy layout
1. Identify the task dir(s) this session worked on
Do not guess — cross-check three signals and keep only the intersection.
# a) active tasks the workspace knows about
bash "$AW" list active
# b) newest active task dir (both layouts: dated + flat legacy)
find "$WS/working" -mindepth 5 -maxdepth 5 -name README.md 2>/dev/null
find "$WS/working" -mindepth 2 -maxdepth 2 -name README.md 2>/dev/null
# c) files this session actually touched (activity tracker)
today=$(date +%Y%m%d)
for f in /tmp/claude-session-*-${today}.jsonl /tmp/claude-session-${today}.jsonl; do
[ -f "$f" ] && jq -r 'select(.file!="") | .file' "$f" 2>/dev/null
done | sort -u
- The canonical task id is
yyyy-mm-dd-slug; on disk the leaf folder is just theslugunderworking/YYYY/MM/DD/.listprints ids; thefindgives you dirs. - Match the touched-files list against what you remember doing this turn. A task that
only shows up in
list activebut you never touched this session → leave it alone. - If exactly one active task and it's obviously the one you worked on, proceed with it as the primary. If several, decide which is primary (still in-flight, gets the NEXT.md) vs which are done.
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.
- 6d ago First seen · 241 lines · 34 tokens per session scan A 298997d033fa
land is a command published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 2,901 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 2026-09-03.
Other commands, from other repositories
gws-tasks
List, create, complete, and manage Google Tasks.
gws-standup
Generate a standup report combining today's calendar and tasks.
status
Display project status, active tracks, and next actions.
decision
Record, list, and manage project decisions with rationale tracking.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
sprint
Équipe de Développement Sprint - Implémentation parallèle de stories utilisant les Agent Teams.