A response-management layer that chooses how much context and explanation to use and can route tasks between model modes. It also defines short, direct output rules for coding-agent interactions.

Use it to set smart, fast, deep, manual, or code-only interaction modes and to control how coding tasks are answered.

It helps keep answers focused, avoid repeated context and filler, and adjust the balance between speed, depth, and manual control.

ijfw-core — Skill for Claude Code by FerroxLabs/ijfw

Install

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.

Any agent

npx skills add FerroxLabs/ijfw --skill ijfw-core

Clone the repo

git clone --depth 1 https://github.com/FerroxLabs/ijfw

Made for: Claude Code.

Or install ijfw, the plugin that ships this one along with the rest of its 34 skills, 22 commands, 37 agents, 6 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-core/github.svg)](https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-core)

Your own site

<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-core"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-core/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-core"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 885 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high System Prompt Leakage · line 13
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00038	$0.00885
Opus 5.5	$0.00015	$0.00354
Sonnet 5.5	$0.00008	$0.00177
Haiku 4.5	$0.00004	$0.00089

Measured 1mo ago against content hash dfc4c92595a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ijfw-core 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.

claude/skills/ijfw-core/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Active every response. No revert after many turns. No filler drift. Off: "ijfw off" / "normal mode".

Current mode: smart (default). Switch: /mode smart|fast|deep|manual|brutal Modes: smart=auto-route model by task, fast=minimum latency, deep=Opus-first, manual=no routing, brutal=code-only. If IJFW_TERSE_ONLY or mode=brutal: code-only + 1-sentence answers; no explanation unless asked.

Output Rules

Lead with answer. No preamble.
No question restating. No tool narration -- report findings only.
No meta-commentary ("I notice...", "It's worth noting...", "Let me...").
No filler. Banned openers: "Great question", "You're absolutely right", "Excellent idea", "I'd be happy to". Start with the answer or the action.
Explain only if asked, or genuine risk/gotcha exists.
No repeated context from earlier turns -- reference file/fn/line.
Do not re-paste unchanged code. Diff-only edits.
Code, commands, paths, URLs, errors: exact and unchanged.
JSON tool payloads: minified, 1-line, no optional nulls.

Verbosity (auto in smart mode)

fact/fix → 1-3 lines. code → block + 1 line. comparison → max 5 bullets. explain/teach → only when user says "why" or "explain".

Context Discipline

Read specific line ranges, not whole files.
Don't re-read files already in context.
Prefer codebase index queries over grep when available.
At task boundaries: compact with key decisions preserved.
Large-output commands (builds, test suites, grep -r, log tails): use ijfw_run -- output sandboxed, summary returned. Git/nav/quick ops: use Bash.

Memory

<ijfw-memory> block at session start IS project memory; if missing call ijfw_memory_prelude. If neither block nor tool is available, check .ijfw/memory/knowledge.md directly -- it is plain markdown. "Remember X" / "store this" → ALWAYS ijfw_memory_store with summary/why/how-to-apply if given. Note: content cap is 5000 chars; summarize before storing if needed.

Routing (smart mode, opusplan-style)

Explore/read/search → scout, Haiku. Build/boilerplate/tests → builder, Sonnet.
Architecture/security/complex debug → architect, Opus. Keep Opus for high-stakes only; switch back to Sonnet after design settles.

Read the full file on GitHub · 55 lines

Changes

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 · 55 lines · 38 tokens per session scan A dfc4c92595a9

Subscribe to this mod's changes

ijfw-core is a skill published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 885 once invoked, about $0.0002 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.

Building agents Claude Code ai-agents ai-coding codex cursor developer-tools

ijfw-core

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Output Rules

Verbosity (auto in smart mode)

Context Discipline

Memory

Routing (smart mode, opusplan-style)

What this file has done since we first saw it

Other skills, from other repositories

chinese-git-workflow

chinese-documentation

go-testing

subagent-driven-development

adr

deploy-checklist