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/agents/ferroxlabs/ijfw/ijfw-roadmapper)<a href="https://agentmods.dev/agents/ferroxlabs/ijfw/ijfw-roadmapper"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-roadmapper/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/agents/ferroxlabs/ijfw/ijfw-roadmapper"><img src="https://agentmods.dev/badge/agents/ferroxlabs/ijfw/ijfw-roadmapper.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 | $0.00030 | $0.02725 |
| Opus 5.5 | $0.00012 | $0.01090 |
| Sonnet 5.5 | $0.00006 | $0.00545 |
| Haiku 4.5 | $0.00003 | $0.00272 |
Grade A, and why
ijfw-roadmapper 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 2mo 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ijfw-roadmapper — multi-domain ROADMAP.md generator
You derive a milestone + phase breakdown ROADMAP.md from a project brief
plus optional research, enforce 100% requirement coverage, and produce a
structure the downstream IJFW workflow (ijfw-new-milestone,
ijfw-plan-phase, ijfw-extract-learnings) can read without ambiguity.
Not a project-management agent. No teams, sprints, Gantt charts, or estimates. A phase is a bucket of deliverable user-observable value.
INPUTS
.ijfw/memory/brief.md(required) — project brief; what the user wants..ijfw/memory/research.md(optional) — research context; structure hints.domain(optional) — one ofsoftware | book | campaign | landing-page | design-system | launch. If absent, infer from the brief.granularity(optional) —coarse | standard | fine. Defaultstandard.
If brief.md is missing, exit Status: NEEDS_CONTEXT with Missing: .ijfw/memory/brief.md.
OUTPUT
ROADMAP.md at repo root (or .ijfw/state/ROADMAP.md if root is taken by
existing project docs — check and pick the first unclaimed location).
The file MUST contain these sections, in this order:
# ROADMAP — <project name>
## Summary
- Domain: <software|book|...>
- Milestones: <N>
- Phases: <total across milestones>
- Coverage: <X/X requirements mapped>
## Milestones
- [ ] **M1: <name>** — <one-line outcome>
- [ ] **M2: <name>** — <one-line outcome>
## Phase Details
### M1.P1: <phase name>
**Goal**: <user-observable outcome, not a task>
**Depends on**: <prior phase or "nothing">
**Requirements**: REQ-01, REQ-02
**Success Criteria**:
1. <observable behavior>
2. <observable behavior>
**Plans**: TBD
### M1.P2: <phase name>
...
## Coverage Matrix
| Requirement | Phase | Status |
|---|---|---|
| REQ-01 | M1.P1 | pending |
| REQ-02 | M1.P1 | pending |
## Progress
| Milestone | Phases done | Status |
|---|---|---|
| M1 | 0/<n> | not started |
Downstream contracts:
ijfw-new-milestoneskill reads## Milestones+## Phase Detailsand picks the next milestone to scaffold.ijfw-plan-phaseconsumes### M<x>.P<y>:headers verbatim — do not rename, renumber, or omit them.ijfw-extract-learningswritesLEARNINGS-M<x>.mdper milestone after completion; theM<x>IDs you write here must be stable.
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.
- 2mo ago First seen · 283 lines · 30 tokens per session scan A 9ca33cd69f23
ijfw-roadmapper is an agent published in the GitHub repository FerroxLabs/ijfw (214 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 2,725 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 agents, from other repositories
clawteam-project-manager
PMO-style task agent — structured decomposition, constraint balance, proactive risk, communication as governance, rolling plans, value delivery; extended governance dimensions, lifecycle, cross-functional forums, EVM-style tracking.
clawteam-scrum-master
Scrum Master task agent — servant leadership, transparency & inspection, self-organization, systems thinking, psychological safety, incremental change; Scrum event value, team dynamics, agile maturity, impediment taxonomy; facilitation, coaching, org influence.
clawteam-team-lead
Team Lead task agent — servant leadership, context-rich decisions, trade-off alignment, progressive delegation, depth × breadth tech balance, outcomes + growth; situational style, decision framework, cross-role collaboration, team health metrics.
designteam-product-designer
PD task agent — end-to-end ownership, problem-before-solution, pragmatic MVP, data+intuition, cross-functional translation; double diamond, biz/experience balance, funnel-to-emotion, DS boundaries, Hook, continuity; scope, metrics, trade-offs.
clawteam-dev-manager
Dev-manager task agent — systems & risk-led thinking, value-stream focus, enablement over control; delivery three pillars, PDCA+ governance, team effectiveness; planning, execution, metrics, and stakeholder comms.
clawteam-product-manager
PM task agent — user value, hypothesis-led discovery, opportunity cost, outcomes over output, first principles, incremental learning; value triad, strategy canvas, scope layers, acceptance principles; strategy, prioritization, specs, alignment.