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/tu11aa/squadrant/command-opsnpx skills add tu11aa/squadrant --skill command-opsgit clone --depth 1 https://github.com/tu11aa/squadrantWhat 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 | $0.00048 | $0.01548 |
| Opus 5 | $0.00024 | $0.00774 |
| Sonnet 5 | $0.00010 | $0.00310 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
command-ops 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 yesterday.
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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command Operations
On-demand only. Command is no longer launched by
squadrant launch --all. You were spawned bysquadrant command --task <briefing|learnings-review|wiki-aggregate>to run a single task and exit. Do the task, then exit cleanly — no persistent loop.
Daily Briefing (Session Start)
Run when session starts, or user says "morning", "catch up", "summary":
- Check handoffs from all projects (context from yesterday's sessions):
for vault in $(cat ~/.config/squadrant/config.json | python3 -c "import json,sys; [print(p['spokeVault']) for p in json.loads(sys.stdin.read())['projects'].values()]"); do
echo "=== $(basename $vault) ==="
~/.config/squadrant/scripts/read-handoff.sh "$vault" --keep
done
Handoffs contain: currentState, openBranches, nextSteps, blockedItems, decisions. Use these to understand where each project left off.
- Search claude-mem (
mem-searchskill) for recent activity across all projects. - Read yesterday's logs:
YESTERDAY=$(date -v-1d +"%Y-%m-%d")
for vault in $(cat ~/.config/squadrant/config.json | python3 -c "import json,sys; [print(p['spokeVault']) for p in json.loads(sys.stdin.read())['projects'].values()]"); do
echo "=== $vault ==="
cat "$vault/daily-logs/${YESTERDAY}.md" 2>/dev/null || echo "(no log)"
done
- Run quick standup for context:
squadrant standup --yesterday --raw - Present briefing, then save to
{hubVault}/daily-logs/YYYY-MM-DD.md
Delegation Workflow
When the user gives a task for a project:
1. Identify project
Match to ~/.config/squadrant/config.json.
2. Check for captain workspace
squadrant runtime list
CRITICAL: Match the EXACT captainName from config. Brove ≠ ⚓ brove-captain.
3. Freshness gate (run BEFORE deciding to reuse)
A name match is not sufficient — the workspace may be holding a session from a previous day. Check sessions.json against today before reusing:
TODAY=$(date +%Y-%m-%d)
LAST=$(python3 -c "import json; d=json.load(open('$HOME/.config/squadrant/sessions.json')); print(d.get('workspaces',{}).get('{captainName}',{}).get('lastLaunched',''))" 2>/dev/null)
[ "$LAST" = "$TODAY" ] && echo "fresh" || echo "stale"
fresh→ reuse the existing workspace, proceed to step 5.stale(or no entry) → close the existing workspace, then go to step 4 to respawn sospawn-workspace.shruns its↻ new day — starting fresh sessionpath:squadrant runtime stop <project>
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.
- yesterday First seen · 150 lines · 48 tokens per session scan A 54afadaf6f29
command-ops is a skill published in the GitHub repository tu11aa/squadrant (2 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,548 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…