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 FerroxLabs/ijfw --skill ijfw-metricsgit clone --depth 1 https://github.com/FerroxLabs/ijfwWrote 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/ferroxlabs/ijfw/ijfw-metrics)<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-metrics"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-metrics/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/ferroxlabs/ijfw/ijfw-metrics"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-metrics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00674 |
| Opus 5.5 | $0.00013 | $0.00270 |
| Sonnet 5.5 | $0.00007 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
ijfw-metrics 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IJFW Metrics -- Internal Tracking
Lightweight metrics captured at session boundaries via hooks. Zero per-turn cost. All tracking happens in the Stop hook.
What We Track
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"
}
Derived Metrics (calculated on /ijfw-status)
From the JSONL log, compute:
Efficiency:
- Average turns per session
- Agent distribution (% scout vs builder vs architect)
- Estimated token savings from model routing:
- scout turns x (opus_price - haiku_price) = routing savings
- builder turns x (opus_price - sonnet_price) = routing savings
Quality:
- Sessions with handoff generated (continuity metric)
- Memory operations per session (knowledge accumulation)
- Compaction count (context pressure indicator)
- Skills loaded per session (specialisation usage)
Cost Projection: Using Anthropic pricing (per 1M tokens):
- Haiku: $0.25 input / $1.25 output
- Sonnet: $3 input / $15 output
- Opus: $15 input / $75 output
If smart routing sent 40% of turns to Haiku instead of Opus:
- Savings per 1K output tokens: $73.75 (Opus→Haiku)
- At 50 turns/session, ~500 output tokens/turn average:
- Per session: ~$0.92 saved on routed turns alone
Status Display Format
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
---------------------------------------
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 · 91 lines · 33 tokens per session scan A da092ff2bc49
ijfw-metrics is a skill published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed 5d ago), licensed MIT. It adds 33 tokens to every session and 674 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
subagent-driven-development
A development workflow in which a fresh coding agent implements each independent task, another review checks that task, and a final review examines the complete set of changes.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.