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/ferroxlabs/ijfw/ijfw-workflownpx skills add FerroxLabs/ijfw --skill ijfw-workflowgit 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-workflow)<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-workflow"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-workflow.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 | $0.00070 | $0.03317 |
| Opus 5 | $0.00035 | $0.01658 |
| Sonnet 5 | $0.00014 | $0.00663 |
| Haiku 4.5 | $0.00007 | $0.00332 |
Grade A, and why
ijfw-workflow 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IJFW Workflow
Two modes, same principles, same invariants.
- Quick -- 5 moves, 3-5 minutes, locked brief. For features, fixes, ideas.
- Deep -- 6 required modules + 3 optional, 20-45 minutes. For new projects, major refactors, launches.
Donahoe Loop: BRAINSTORM -> PLAN -> EXECUTE -> VERIFY -> SHIP -> MEASURE
|<--- memory recall at every entry --->|
|<--- Trident cross-audit on request --->|
Detailed downstream procedure (PLAN / EXECUTE / VERIFY / SHIP, including wave dispatch, post-DONE pipeline, Phase-E cross-audit): see
references/post-brainstorm-workflow.md. Deep-mode optional modules (EXTERNAL BRIEF / ANTI-SCOPE / TRIDENT CROSS-CRITIQUE): seereferences/deep-mode-optional.md.
RUNTIME BOOTSTRAP AND FALLBACKS
Before the first workflow write or command invocation, inspect whether .ijfw/memory/ exists so the auto-picker and empty-state opener can use that signal accurately. Then ensure .ijfw/memory/ and .planning/ exist before writing artifacts. If the ijfw CLI is unavailable in this session, continue with markdown files and visible chat checklists, then state the exact CLI command the user can run later. Optional commands such as ijfw cross, ijfw design, ijfw recover, ijfw blackboard, ijfw team, and ijfw swarm must degrade to explicit written artifacts instead of blocking the workflow.
AUTO-PICKER (runs first, every time)
Deterministic signals, visible reasoning, no friction.
| Signal | Points towards |
|---|---|
| Prompt < 15 words | Quick |
| Prompt has clear verb + object | Quick |
| Vague verbs alone ("improve", "fix", "handle", "deal with") | Deep |
| "New project", "major refactor", "launch", "design" | Deep |
Project dir has no .ijfw/memory/ |
Deep |
| Explicit "brainstorm", "quick idea", "just sketch" | Quick |
Protocol:
- Read signals silently.
- Say in one line:
Reading this as <Quick|Deep> -- <reason>. Say "go deeper" / "just quick" to switch. - If signals tie, ask once:
Quick or Deep?Accept any affirmative shortcut ("q" / "d"). - Start immediately. The user should never wait on a modal.
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- lib/dispatch-helpers.md 5.6 KB
- prompts/post-done-self-check.md 2.1 KB
- prompts/quality-reviewer.md 4.8 KB
- prompts/spec-reviewer.md 3.5 KB
- references/build-phase.md 11 KB
- references/deep-mode-optional.md 996 B
- references/donahoe-principles.md 2.7 KB
- references/post-brainstorm-workflow.md 14 KB
- references/score-examples.md 4.4 KB
- references/ship-phase.md 2.1 KB
- references/team-templates.md 2.9 KB
- references/think-phase.md 16 KB
- templates/book.phases.md 4.0 KB
- templates/campaign.phases.md 4.0 KB
- templates/design-system.phases.md 4.2 KB
- templates/landing-page.phases.md 4.2 KB
- templates/launch.phases.md 4.5 KB
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 · 221 lines · 70 tokens per session scan A 8e28b812741d
ijfw-workflow is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 5d ago), licensed MIT. It adds 70 tokens to every session and 3,317 once invoked, about $0.0003 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 skills, from other repositories
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
subagent-driven-development
当在当前会话中执行包含独立任务的实现计划时使用.
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.