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/ijfw-plangit 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/ijfw-plan)<a href="https://agentmods.dev/commands/ferroxlabs/ijfw/ijfw-plan"><img src="https://agentmods.dev/badge/commands/ferroxlabs/ijfw/ijfw-plan.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 | $0.00036 | $0.00533 |
| Opus 5 | $0.00018 | $0.00267 |
| Sonnet 5 | $0.00007 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
ijfw-plan 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 6d 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.
What it actually says
Jump straight into the IJFW workflow Plan phase without walking through Discovery and Research first. Use this when you already know what you're building and want to move into structured planning now.
Quick mode (Q2): Draft a focused plan of up to 10 tasks, each with a clear deliverable and success criteria. Present it for approval, then execute.
Deep mode (D3): Break the work into phases → milestones → tasks. Each task
gets a deliverable, success criteria, file list, dependencies, and blast radius.
Output lands in .ijfw/memory/plan.md (fallback: .planning/**/PLAN.md). The
full PLAN AUDIT gate runs before execution begins.
This command invokes ijfw-workflow at the Plan phase directly. IJFW owns the
full loop from here: plan → audit → execute → verify → ship. No external plugin
hand-off.
Natural triggers: "let's plan this", "make a plan", "planning phase", "I know what to build, let's plan it."
If you have an existing brief.md, this command reads it as context automatically.
If not, it asks one clarifying question to establish scope before drafting.
GATE: Plan phase ends at the PLAN AUDIT gate -- every requirement has a task, no scope drops, dependencies ordered. Gate must pass before execution begins.
Deep mode asks a time-budget question before drafting. Deep mode offers a four-mode review after plan-check.
Resume intent pattern: If user says resume, resume plan, /ijfw-plan resume, or continue plan:
- Load
.ijfw/state/plan-hold.md. If missing: reply "No plan on hold. Start a fresh plan with/ijfw-plan." and stop. - Echo the recorded reason + unresolved gaps to the user so they know what was blocking.
- Ask AskUserQuestion: "Has this changed? Unblock and continue, or keep on hold?"
- Option A: "Unblock + continue" -> re-run plan-check, re-offer four-mode review (Step 7).
- Option B: "Keep on hold" -> no-op, close.
- On unblock: annotate
.ijfw/state/plan-hold.mdwithresolved_at: <now>(or delete), re-run plan-check Step 7.
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.
- 6d ago First seen · 40 lines · 36 tokens per session scan A b541bd4d8eba
ijfw-plan is a command published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 533 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
constitution
根据交互输入或已提供原则创建或更新项目章程，并确保相关模板保持同步。.
core-review
Review code changes against SpecOps project-specific patterns. Catches recurring failure modes from real PRs — tool abstraction violations, generated file drift, cross-platform gaps, variable inconsistencies, and more. Complements full-review-gate (generic quality) and pr-fix (applying bot comments).
resolve-conflicts
Resolve merge conflicts on a GitHub PR by merging the base branch into the PR branch in an isolated git worktree, with JSON/markdown-aware conflict resolution.
ship-pr
Commit all changes to a new branch, push, and open a PR for review. The original branch stays clean.
implement
Execute implementation by processing atomic task files one at a time with Context Pinning (Atomic Traceability Model).
delegate
Delegate a coding task to the Cursor CLI agent (Composer by default).