/ijfw-execute
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name]
$ npx -y skills add FerroxLabs/ijfw --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/ijfw-execute
Context preview
What this command does when you run it.
Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name]
Command definition
ijfw-execute.mdname: ijfw-execute
description: "Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name]"
Jump straight into the IJFW workflow Execute phase. Use this when a plan is already approved and you're ready to build.
**Quick mode (Q3):** Work through tasks in sequence. Run tests and verification after each. Store key decisions in memory. One-keystroke: `/ijfw-execute`.
**Deep mode (D4):** Dispatch tasks to the project team agents set up during Discovery. Specialist agents run in parallel where tasks are independent. Human checkpoints fire at each phase boundary. Atomic commits for code changes. `progress.md` updates after every phase.
This command invokes `ijfw-workflow` at the Execute phase directly. IJFW drives the full execution loop via the `Agent` tool -- no external plugin hand-off. Every task transition creates a visible task entry so you can see progress in real time.
**Natural triggers:** "start building", "execute the plan", "let's go", "build it", "kick off execution."
If no `plan.md` exists, this command offers a 2-minute Quick Plan pass first before executing -- skipping planning reliably causes scope drift.
**Deep mode runs tasks under completion contracts with max-iter=3.** Each task in Deep mode requires a completion contract (defined in plan.md). The Ralph loop runs up to 3 iterations per task, re-dispatching with failure feedback on each failed criterion. If all criteria pass: VERIFIED. If max iterations exhausted or stagnation detected (two identical result sets): ISSUE persisted to `.ijfw/state/execute-issues.json`.
**resolve sub-command:** `/ijfw-execute resolve <iss_id> <note>` resolves a ledger entry. Matches: "resolve issue <id>", "mark <id> resolved", etc. 1. Load `.ijfw/state/execute-issues.json`. 2. Find entry by `id`; set `status: resolved`, `resolution: accepted` (or `deferred` / `reworked` per note), `resolved_at: <now ISO-8601>`. 3. Write back atomically (temp file + rename). 4. Emit one-line receipt: `Resolved iss_001 (accepted). 0 unresolved issues remain.`
Alternative: next successful execute of the same `task_id` auto-resolves all unresolved entries for that task.
**Ledger gate:** Before starting execution, read `.ijfw/state/execute-issues.json` (treat missing file as zero issues). If any entry has `status: unresolved`, halt and list the issues -- resolve them first or use the resolve sub-command.
**GATE:** Execute phase ends at the PHASE AUDIT gate -- all phase tasks complete, brief still accurate, memory updated. Gate runs at each phase boundary.
Read more
name: ijfw-execute description: "Jump directly to the IJFW workflow Execute phase (Deep D4 / Quick Q3). Usage: /ijfw-execute [task or phase name]"
Jump straight into the IJFW workflow Execute phase. Use this when a plan is already approved and you're ready to build.
**Quick mode (Q3):** Work through tasks in sequence. Run tests and verification after each. Store key decisions in memory. One-keystroke: `/ijfw-execute`.
**Deep mode (D4):** Dispatch tasks to the project team agents set up during Discovery. Specialist agents run in parallel where tasks are independent. Human checkpoints fire at each phase boundary. Atomic commits for code changes. `progress.md` updates after every phase.
This command invokes `ijfw-workflow` at the Execute phase directly. IJFW drives the full execution loop via the `Agent` tool -- no external plugin hand-off. Every task transition creates a visible task entry so you can see progress in real time.
**Natural triggers:** "start building", "execute the plan", "let's go", "build it", "kick off execution."
If no `plan.md` exists, this command offers a 2-minute Quick Plan pass first before executing -- skipping planning reliably causes scope drift.
**Deep mode runs tasks under completion contracts with max-iter=3.** Each task in Deep mode requires a completion contract (defined in plan.md). The Ralph loop runs up to 3 iterations per task, re-dispatching with failure feedback on each failed criterion. If all criteria pass: VERIFIED. If max iterations exhausted or stagnation detected (two identical result sets): ISSUE persisted to `.ijfw/state/execute-issues.json`.
**resolve sub-command:** `/ijfw-execute resolve <iss_id> <note>` resolves a ledger entry. Matches: "resolve issue <id>", "mark <id> resolved", etc. 1. Load `.ijfw/state/execute-issues.json`. 2. Find entry by `id`; set `status: resolved`, `resolution: accepted` (or `deferred` / `reworked` per note), `resolved_at: <now ISO-8601>`. 3. Write back atomically (temp file + rename). 4. Emit one-line receipt: `Resolved iss_001 (accepted). 0 unresolved issues remain.`
Alternative: next successful execute of the same `task_id` auto-resolves all unresolved entries for that task.
**Ledger gate:** Before starting execution, read `.ijfw/state/execute-issues.json` (treat missing file as zero issues). If any entry has `status: unresolved`, halt and list the issues -- resolve them first or use the resolve sub-command.
**GATE:** Execute phase ends at the PHASE AUDIT gate -- all phase tasks complete, brief still accurate, memory updated. Gate runs at each phase boundary.
IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.
Repo: FerroxLabs/ijfw
Other commands on ijfw.
- /compress
Compress a memory/context file into terse form. Saves ~40-50% tokens per session. Usage: /compress <filepath>
Open command - /consolidate
Dream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
Open command - /cross-audit
Second-model review. Picks an auditor (codex/gemini/opencode/aider/copilot), excludes the caller, writes a prompt to paste, reads the response back. Usage: /cross-audit [--with <id> | list | compare] <target>
Open command - /cross-critique
Adversarial multi-angle critique. All three auditors fire in parallel (codex=technical, gemini=strategic, claude=ux). Counter-args ranked by rebuttal survival score, not raw severity. Usage: /cross-critique [--with <id> | list | compare] <target>
Open command - /cross-research
Two-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via fresh Claude session. Usage: /cross-research [--with <id> | list | compare] <target>
Open command - /doctor
Run IJFW health check (files, MCP server, hooks, memory, caps, framing)
Open command

