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 skills/wlfghdr/agentic-kb/kb-roadmapnpx skills add wlfghdr/agentic-kb --skill kb-roadmapgit clone --depth 1 https://github.com/wlfghdr/agentic-kbWrote 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/wlfghdr/agentic-kb/kb-roadmap)<a href="https://agentmods.dev/skills/wlfghdr/agentic-kb/kb-roadmap"><img src="https://agentmods.dev/badge/skills/wlfghdr/agentic-kb/kb-roadmap.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 5.1 | $0.00084 | $0.04346 |
| Opus 5 | $0.00042 | $0.02173 |
| Sonnet 5 | $0.00017 | $0.00869 |
| Haiku 4.5 | $0.00008 | $0.00435 |
Grade A, and why
kb-roadmap 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 5d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: KB Roadmap
Organizations always have at least two sources of planning truth — tickets and the repository, milestones and delivery, OKRs and commits. They drift. Manual reconciliation is expensive and always stale. This skill closes the loop: it ingests plan + delivery, correlates them across a five-tier ladder, and produces a roadmap artifact that says what is planned, what is delivered, and where the two disagree.
This skill is vendor-neutral. All vocabulary specific to a particular tracker, repository host, or organization lives in the adopter's .kb-config/layers.yaml and .kb-config/artifacts.yaml, never in this skill.
The roadmap is a product-management artifact, not just a tracker report. Its job is to make planned customer/user value, confidence, delivery reality, and source traceability visible in one place.
The skill resolves its roadmap: block from the active layer entry in .kb-config/layers.yaml and can normalize read-only tracker inputs from that layer's connections.trackers[] declarations when legacy roadmap.issue-trackers[] entries are absent.
When to invoke
Invoke whenever the user:
- Types
/kb roadmap(optionally followed by--since,--scope,--workstream,digest,sync). - Asks for a roadmap, status, or deviation report that spans both a planning tool and a repository.
- Asks "what shipped vs. what was planned?", "where does my roadmap drift from reality?", or "which tickets have no code?"
The single command model
One entry point — /kb roadmap — with context-driven subcommands:
| Input | Action |
|---|---|
/kb roadmap |
Generate artifact with default scope + timeframe |
/kb roadmap --since YYYY-MM-DD |
Custom baseline |
/kb roadmap --scope <name> |
Scope to a workstream declared in .kb-config/layers.yaml |
/kb roadmap digest |
Pull latest plan + delivery state; compute delta; do not render |
/kb roadmap sync |
Propose plan-source updates based on delivery reality (dry-run default) |
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 3.2 KB
- references/adapters.md 6.3 KB
- references/artifact-contract.md 4.2 KB
- references/audit.md 7.4 KB
- references/authoring-commands.md 10 KB
- references/command-reference.md 6.8 KB
- references/config-schema.md 8.3 KB
- references/correlation-ladder.md 4.5 KB
- references/discuss-mode.md 2.1 KB
- references/folder-layout.md 3.9 KB
- references/html-template.md 8.2 KB
- references/issue-trackers.md 5.9 KB
- references/journey-grounding.md 7.4 KB
- references/mismatch-findings.md 2.8 KB
- references/phase-gates.md 3.4 KB
- references/state-machine.md 3.5 KB
- scripts/kb_roadmap.py 96 KB runs code
- templates/roadmap.html.hbs 11 KB
- templates/roadmap.json.schema.json 4.3 KB
- templates/roadmap.md.hbs 3.3 KB
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.
- 5d ago First seen · 264 lines · 84 tokens per session scan A 1cc133ce5ec2
kb-roadmap is a skill published in the GitHub repository wlfghdr/agentic-kb (10 stars, last pushed 20d ago), licensed Apache-2.0. It adds 84 tokens to every session and 4,346 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.