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-executegit 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-execute)<a href="https://agentmods.dev/commands/ferroxlabs/ijfw/ijfw-execute"><img src="https://agentmods.dev/badge/commands/ferroxlabs/ijfw/ijfw-execute.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 | $0.00036 | $0.00615 |
| Opus 5 | $0.00018 | $0.00308 |
| Sonnet 5 | $0.00007 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
ijfw-execute 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 3d 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 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 ", "mark resolved", etc.
- Load
.ijfw/state/execute-issues.json. - Find entry by
id; setstatus: resolved,resolution: accepted(ordeferred/reworkedper note),resolved_at: <now ISO-8601>. - Write back atomically (temp file + rename).
- 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.
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.
- 3d ago First seen · 52 lines · 36 tokens per session scan A c09d32927439
ijfw-execute is a command published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 10d ago), licensed MIT. It adds 36 tokens to every session and 615 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
taskstoissues
基于现有设计制品，将任务转换为可执行、带依赖顺序的 GitHub Issues。.
meta-theory
Run the MetaKim meta-theory governance dispatcher.
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).
full-review-gate
Perform a comprehensive repository code review in an isolated worktree. Fix P0/P1 findings and ship them as a PR targeting the current branch.
ship-pr
Commit all changes to a new branch, push, and open a PR for review. The original branch stays clean.
plan
Execute the implementation planning workflow using the plan template to generate design artifacts.