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 skills add FerroxLabs/ijfw --skill ijfw-new-milestonegit 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-new-milestone)<a href="https://agentmods.dev/skills/ferroxlabs/ijfw/ijfw-new-milestone"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-new-milestone/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/skills/ferroxlabs/ijfw/ijfw-new-milestone"><img src="https://agentmods.dev/badge/skills/ferroxlabs/ijfw/ijfw-new-milestone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.01781 |
| Opus 5 | $0.00032 | $0.00890 |
| Sonnet 5 | $0.00013 | $0.00356 |
| Haiku 4.5 | $0.00006 | $0.00178 |
Grade A, and why
ijfw-new-milestone 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IJFW New Milestone
Kick off a new milestone cycle on an existing project. Brownfield equivalent of project bootstrap: project exists, prior milestones shipped, you need a scoped plan for the next iteration.
Domain-agnostic. Works for software releases (v1.2 → v1.3), book chapters (Ch 4 → Ch 5), campaign waves (Wave 2 → Wave 3), design-system tiers (Foundation → Components → Patterns).
Optional $ARGUMENTS: milestone name (e.g. v1.6 Notifications, Chapter 5: Adversarial Models). Ask inline if absent.
1 — Load prior context
Read in order:
.planning/PROJECT.md— core value, validated outcomes, decisions.planning/ROADMAP.md— what shipped, last milestone number/name.planning/MILESTONES.md— historical log (if present).planning/STATE.md— pending todos, blockers carried forward- Latest
.planning/<prior-milestone>/LEARNINGS.md(if present) — dispatchijfw-extract-learningsagent on the prior milestone first if missing; learnings inform what to do differently this cycle.
If .planning/ROADMAP.md is absent, dispatch ijfw-roadmapper agent to scaffold one from PROJECT.md, then resume here.
2 — Determine next milestone identifier
Parse the last milestone from MILESTONES.md or ROADMAP.md. Suggest the next per project convention:
- Semver:
v1.5 → v1.6(minor) /v1.5 → v2.0(major) - Chapter / Wave:
N → N+1 - Free-form: ask the user
Confirm before writing anything.
3 — Gather scope (adaptive)
Ask one open question: What do you want to ship in this milestone? (one sentence)
Then probe by domain bucket (pick what fits, skip the rest):
- Capabilities — new functionality / features / chapters / campaign assets
- Quality — coverage, perf, accessibility, edit passes, brand consistency
- Trust — security, audits, fact-checks, compliance, source alignment
- Ecosystem — integrations, partners, distribution channels, platform support
- Reduction — deprecations, cuts, tightening, scope-creep kills
Per activated bucket ask: Table stakes vs differentiators? Table stakes go in; differentiators debated.
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 · 180 lines · 63 tokens per session scan A 5c881517dbd4
ijfw-new-milestone is a skill published in the GitHub repository FerroxLabs/ijfw (210 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 1,781 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
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
change-manager
name: change-manager description: Used when the user adds a feature or incrementally changes an existing project that already has Product-Spec.md. Runs the changes/ workflow (propose, apply, verify, archive), aligned with OpenSpec-style SDD while delegating implementation to dev-planner and dev-builder. version: 1.1.0…
product-strategy
A product-planning guide for evaluating requirements, users, scope, priorities, roadmaps, and success measures. It ties proposals to user problems, business value, boundaries, and signals that can be checked.
slice-closure
Decide whether the current slice is ready to close, distinguishing slice completion from full task completion, then persist the result in slice notes and TASKSTATE.md as explicit reviewable closure notes. For single-slice tasks may route directly to delivery. Returns no-op when slice memory would not materially…