ijfw-agents-md
Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent…
Internal session metrics tracking. Auto-triggered at session boundaries. Tracks tokens, agent usage, efficiency gains. View with /ijfw-status.
Claude Code
$ npx -y skills add FerroxLabs/ijfw --skill ijfw-metrics --agent claude-code
Codex
$ npx skills add FerroxLabs/ijfw --skill ijfw-metrics -a codex -y
Cursor
$ npx skills add FerroxLabs/ijfw --skill ijfw-metrics -a cursor -y
Gemini CLI
$ npx skills add FerroxLabs/ijfw --skill ijfw-metrics -a gemini-cli -y
GitHub Copilot
$ npx skills add FerroxLabs/ijfw --skill ijfw-metrics -a github-copilot -y
OpenCode
$ npx skills add FerroxLabs/ijfw --skill ijfw-metrics -a opencode -y
Windsurf
$ npx skills add FerroxLabs/ijfw --skill ijfw-metrics -a windsurf -y
name: ijfw-metrics description: "Internal session metrics tracking. Auto-triggered at session boundaries. Tracks tokens, agent usage, efficiency gains. View with /ijfw-status."
Lightweight metrics captured at session boundaries via hooks. Zero per-turn cost. All tracking happens in the Stop hook.
At each session end, append to `.ijfw/metrics/sessions.jsonl`:
{
"timestamp": "2026-04-13T14:30:00Z",
"session_id": "<session-id>",
"duration_minutes": 45,
"turns": 23,
"mode": "smart",
"effort": "high",
"agents_dispatched": {
"scout": 8,
"builder": 12,
"architect": 3
},
"memory_ops": {
"stores": 5,
"recalls": 2,
"searches": 1
},
"skills_loaded": ["ijfw-core", "ijfw-commit", "ijfw-review"],
"compactions": 1,
"handoff_generated": true,
"routing": "OpenRouter + local model"
}From the JSONL log, compute:
**Efficiency:**
**Quality:**
**Cost Projection:** Using Anthropic pricing (per 1M tokens):
If smart routing sent 40% of turns to Haiku instead of Opus:
When user runs `/ijfw-status` or asks about performance:
IJFW Status Mode: smart | Effort: high | OpenRouter This Session: 12 turns | 3 agents dispatched | 2 decisions stored All Time (47 sessions): Smart routing: 340 turns -> scout, 580 -> builder, 127 -> architect Estimated savings: ~$43 in model routing Memory: 89 decisions, 12 patterns, 4 consolidations Continuity: 94% sessions with handoff Context health: 34% used | Next compact: ~66% threshold ---------------------------------------
Positive framing. Show what IJFW has done for you. Never show negatives or waste metrics.
IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.
Maintain canonical AGENTS.md (open spec). Trigger: 'agents.md', 'update AGENTS.md', or auto-fired by ijfw-team after agent…
Session-end auto-extraction of lessons, errors, fixes, and user feedback into structured memory. Fires at session end. Requires…
Terse conventional commits. Trigger: commit, git commit, /ijfw-commit
Use when a milestone is shipping and you need to archive its artifacts, generate a summary, and seed the next milestone. Trigger:…
Compress memory/context files into terse form. Trigger: /compress, compress file
Use when the user says: 'compute', 'crunch this', 'analyze logs', 'aggregate the data', 'run a script', 'dedupe', 'count by',…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.