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.
git 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-ship)<a href="https://agentmods.dev/commands/ferroxlabs/ijfw/ijfw-ship"><img src="https://agentmods.dev/badge/commands/ferroxlabs/ijfw/ijfw-ship/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.
<a href="https://agentmods.dev/commands/ferroxlabs/ijfw/ijfw-ship"><img src="https://agentmods.dev/badge/commands/ferroxlabs/ijfw/ijfw-ship.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.00581 |
| Opus 5.5 | $0.00013 | $0.00232 |
| Sonnet 5.5 | $0.00006 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
ijfw-ship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the Ship phase of the IJFW workflow. This is the final phase -- pre-flight checks, deployment, monitoring, rollback plan, documentation, and memory update.
Ship checklist:
- Changelog updated with what shipped
- Deployment steps verified (or deployment executed if automated)
- Monitoring and alerting confirmed in place
- Rollback plan documented
- User-facing documentation current
- IJFW memory updated with the full project summary
Donahoe principles enforced at ship:
- P15: Updates invisible to users -- no action required from them
- P20: Works on all target platforms
- P21: Pricing respects the user (no surprise costs introduced)
Ledger gate (blocks ship): Before the SHIP GATE runs, read .ijfw/state/execute-issues.json:
read_issues() {
local f=".ijfw/state/execute-issues.json"
[ -f "$f" ] || { printf '{"issues":[]}'; return; }
cat "$f"
}
If any entry has status: unresolved (any kind), ship is refused:
ISSUE: ship-blocked-by-unresolved-issues
count: <N>
ids: [iss_001, iss_002]
action: resolve all issues before shipping
Missing file = zero issues (day-1 fresh-install protection). Resolved and absent entries do not block ship.
Before running, the SHIP GATE re-reads the original brief and confirms what was built matches what was asked. If gaps remain, ship is held until they close.
This command invokes ijfw-workflow at the D6 Ship phase directly.
GATE: The SHIP GATE must pass before deployment proceeds -- original brief re-read, changelog updated, monitoring confirmed, rollback plan documented.
Confidence declaration (required before push/publish): Every ship-readiness
claim is tagged VERIFIED / LIKELY / GUESSING / ISSUE. Ship proceeds only when
every blocking claim is VERIFIED (live-run command with raw output) or LIKELY
with explicit user acknowledgement. GUESSING or ISSUE halts the ship. Publish
operations (git push, git tag v*, npm publish) require the user's
explicit push-word ("push it" / "ship it" / "tag and push") -- no substitute
authorization accepted. See feedback_push_back_on_irreversible.md.
Natural triggers: "ship it", "deploy", "let's ship", "go live", "time to ship", "wrap this up."
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 · 63 lines · 32 tokens per session scan A 69c275b3fcc2
ijfw-ship is a command published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 581 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
pr-package
Prepare a GitHub PR delivery package (branch, commits, PR title and body, reviewer notes) from the real git diff against an explicit base branch, persisted as PRPACKAGE.md, never inventing work outside the diff. Use when scope is done and diff is stable. Do not use mid-implementation, for a branch name (use…
reqforge-greenkeeper
Diagnose and fix ReqForge repository release gate failures.
release-builder
Build, audit, and publish project to target channel.
ship
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
publish
Publish oh-my-opencode to npm via GitHub Actions workflow.
get-unpublished-changes
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer.