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 commands/ferroxlabs/ijfw/modegit 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/commands/ferroxlabs/ijfw/mode)<a href="https://agentmods.dev/commands/ferroxlabs/ijfw/mode"><img src="https://agentmods.dev/badge/commands/ferroxlabs/ijfw/mode.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00315 |
| Opus 5 | $0.00011 | $0.00158 |
| Sonnet 5 | $0.00004 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
mode 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 today.
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.
What it actually says
Switch the active IJFW mode. Acknowledge with one line.
smart (default): Auto-routes models, effort, and verbosity by task type. Routine → scout/builder, terse. Complex → architect, thorough. Teaching → normal verbosity.
fast: Maximum efficiency. Cheapest viable model. Low effort. Ultra-terse. Aggressive compaction. For blasting through known tasks.
deep: Maximum quality. Best model. High/max effort. Self-verification on. Plan-then-execute enforced. Normal verbosity. For architecture, security, complex debug.
manual: All IJFW automation off. User controls /model, /effort, verbosity. Output rules still active but overridable. For power users.
brutal: Caveman mode -- 1-sentence answers, code-only, no explanation unless user asks "why" or "explain". Reasoning/thinking preserved, output constrained. Sets IJFW_TERSE_ONLY=1. For blast-mode task execution.
Natural language triggers also work:
- "go fast" / "speed mode" → fast
- "think deeper" / "be thorough" → deep
- "back to normal" / "auto" → smart
- "be brutal" / "caveman mode" / "ultra-terse" → brutal
Mode persists until changed or session ends.
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.
- today First seen · 31 lines · 22 tokens per session scan A 59a42e9b4a06
mode is a command published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 315 once invoked, about $0.0001 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 2026-09-05.
Other commands, from other repositories
nopua-en
Manually activate NoPUA clarity mode when stuck — identify the failure pattern and work through stop → observe → transform → act → transcend, driven by wisdom rather than fear.
approve-proposed
Atomically persist every file marked PROPOSED in the most recent prior assistant turn's ### Artifact changes block. Single-command idiom that closes the two-step latency in ADR-0001's PROPOSED-by-default contract; the user reviews proposals in Ask/Plan mode, then runs this once to write all of them. Use when the prior…
stack-currency-check
Verify that the patterns the model is about to use for a given framework+version are current per official docs, and cache the result as CURRENTPATTERNS.md at the project level. Prevents the "gold-standard audit" anti-pattern where training-data defaults ship outdated patterns (e.g. Supabase getSession when getUser is…
apply-sweep-triage
Persist the user's triage decisions (apply, decline, discuss) from a SWEEP snapshot into REVIEWPREFERENCES.md so future sweeps suppress declined findings and track applied fixes. Use after the user has edited the triage values in a SWEEP snapshot file produced by repo-consistency-sweep. Do not use when no sweep…
team-update
Write a simple, natural English status update for any team channel (Slack, Discord, Teams, email, GitHub PR comment, standup notes), short, grounded, and professional. Channel-portable. Use when the user wants to communicate progress quickly to teammates or reviewers, implementation or planning has reached a…
init
First-time setup. Auto-detects installed AI CLIs and configures targets.